ABSTRACT. 互联网新闻已被很多研究用于物价指数的监测和预测。但在对于某一分类别物价的舆情指数构建过程中，经常会出现舆情观点新闻缺失的问题。在对没有舆情讨论的时点的舆情数据进行数据补齐的时候，不仅需要考虑该缺失数据时点前后的舆情值，同时也要考虑该时点其他相关主题的舆情值。为了更好地刻画不同相关主题下新闻舆情之间的复杂关联关系，本文提出了一种基于图神经网络自学习模型（AGNN）的舆情指数网络构建方法。这种方法将九个食品相关舆情指数作为网络节点，相应的量化后的日度舆情观点值作为时间序列，设计了一个图神经网络模型对存在的隐性图结构进行学习，构建成动态舆情指数网络，实现对于稀疏的细项新闻观点取值的补齐。为验证所提出的舆情指数网络模型的有效性，我们利用所提出的基于AGNN舆情指数网络的模型对各个食品分类相关的新闻观点数据缺失进行填补，并将其用于消费者价格指数食品项的预测。与其他数据补齐方式相比，我们经过我们提出的模型补齐的舆情数据对食品价格的预测精度提升最大。可见，本研究所提出的舆情指数网络模型能够更有效地刻画食品相关不同主题下，该方法对于其他类似的舆情指数集合建模问题也有一定的借鉴价值。

ABSTRACT. Deep learning (DL) models have significantly improved the performance of text classification and text regression tasks. However, DL models are often strikingly vulnerable to adversarial attacks. Many researchers have aimed to develop adversarial attacks against DL models in realistic black-box settings (i.e., assumes no model knowledge is accessible to attackers) that typically operate with a two-phase framework: (1) sensitivity estimation through gradient-based or deletion-based methods to evaluate the sensitivity of each token to the prediction of the target model, and (2) perturbation execution to craft adversarial examples based on the estimated token sensitivity. However, gradient-based and deletion-based methods used to estimate sensitivity often face issues of capturing the directionality of tokens and overlapping token sensitivities, respectively. In this study, we propose a novel eXplanation-based method for Adversarial Text Attacks (XATA) that leverages additive feature attribution explainable methods, namely LIME or SHAP, to measure the sensitivity of input tokens when crafting black-box adversarial attacks on DL models performing text classification or text regression. We evaluated XATA’s attack performance on DL models executing text classification on three datasets (IMDB Movie Review, Yelp Reviews-Polarity, and Amazon Reviews-Polarity) and DL models conducting text regression on three datasets (My Personality, Drug Review, and CommonLit Readability). The proposed XATA outperformed the existing gradient-based and deletion-based adversarial attack baselines in both tasks. These findings indicate that the ever-growing research focused on improving the explainability of DL models with additive feature attribution explainable methods can provide attackers with weapons to launch targeted adversarial attacks.

ABSTRACT. There exists an algorithm paradox which scholars have still not paid attention to in the gig economy. This paper builds a moderated-mediation model to explore and validate the specific boundary condition and impact mechanism of such an algorithm paradox. Results based on 314 data collected from Chinese gig workers find that, algorithmic monitoring can enhance gig workers’ organizational identification, but through the mediating effect of job flexibility, algorithmic monitoring can indirectly decrease gig workers’ organizational identification. Criteria control can not only mitigate the negative relationship between algorithmic monitoring and job flexibility, but also mitigate the negative relationship between algorithmic monitoring and organizational identification mediated by job flexibility. These findings prove the reality of the algorithm paradox and discuss theoretical and practical implications about how to enhance gig workers to identify with the platform.

ABSTRACT. In this paper, we investigate a two-echelon fresh product supply chain composed of a supplier and a distributor. The expression of preservation effort and order quantity are obtained under three kinds of preservation investment methods, as well as the intrinsic correlation mechanism among these decisions. With the aim of maximizing profit, the optimal preservation decision is made. This study shows that, joint investment in preservation is always the best way for both parties. When the gap between wholesale price and produce cost is small, the joint investment of supplier and distributor can be approximately equivalent to the investment of distributor alone. Therefore, distributors should take the initiative to undertake the preservation investment in order to maximize profits, while suppliers should avoid undertaking the investment alone.

ABSTRACT. Although mobile promotions are still a major marketing method in recent years, conversion rates for mobile promotions are not very high. How to improve the effectiveness of mobile promotion is still a challenge for company. Based on probability distance and construal level theory, this paper explores the influence of construal-matching effect on consumer repurchase behavior by using the large-scale field experiment in a low-cost airlines. The results show that the matching between low probability distance and high construal level has a significant negative effect on consumer repurchase behavior, while the matching between high probability distance and low construal level has a significant positive effect on consumer repurchase behavior. The differences of this result and the construal-matching effect are discussed. Furthermore, the moderating effects of probability distance and individual characteristics on matching effect also are discussed. This research has guiding significance for marketing, consumer relationship management, and customized service strategy.

ABSTRACT. Consumer purchase prediction is very important for strategy formulation and consumer segmentation. In particular, airlines have to target groups before implementing the operational strategy with the competition increases. However, due to the higher dimensions and a large number data missing in airlines, how to effectively predict the repurchase of consumers has become an urgent problem. This paper proposes a novel ensemble algorithm framework for predicting the binary classification based on evidence theory. The results show that the accuracy of the ensemble algorithm based on evidence theory is more than 90% using the public datasets. Further, this paper uses this algorithm model to predict the repurchase possibility of consumers in airlines. The results show that the performance and accuracy of this algorithm are improved compared with common used ensemble algorithms. This study has guiding and theoretical significance for consumer purchase prediction, the application of evidence theory and precision marketing

ABSTRACT. Despite members is high social identity and more loyalty to a product or brand, the existing marketing literatures offers little guidance on how to promote members’ actual purchase behavior based on the matching consistency and construal level theory. To address this gap, the current research examines that the matching consistency effect between predicted purchase probability and the construal level of promotions advertising on the repurchase behavior of members based on a large field experiment in airlines. The findings show that the matching effect between promotional messages with concrete or feasibility information and high purchase probability has more likely to promote members' repurchase behavior, while the matching effect between promotional messages with abstract or desirability information and low purchase probability has not any influence on members' repurchase behavior. This study has theoretical and practical guiding for the researches on marketing and customer management.

ABSTRACT. Based on the company financial reports and employee reviews on the Glassdoor platform, a new data sources, this paper employs the Word2vec model to mine the company's declared culture and employee perception culture from two types of texts in the perspective of corporate culture. On this basis, a new measurement of employee-organization fit is proposed. Then we examine the impact of employee-organization fit and employee online rating on company value. The results show that: under the new measurement method, there is a certain difference between the company's declared culture and employees' perceived culture as a whole, and the employee-organization fit of most companies is at a high level; employee-organization fit has a positive impact on company value, and it will enhance the promotion effect of employee online rating on company value. This paper makes a new attempt to measure employee-organization fit by using new data, and clarifies the value of employee online rating and employee-organization fit, which has theoretical and practical guiding significance for related research and organizational management.

ABSTRACT. 城市社区是国家基层治理的基本单元，在公共卫生事件应急处置中发挥重要作用。为探索城市社区突发公共卫生事件应急处置能力影响因素，以结构功能主义为研究视角，使用扎根理论编码方法，借助质性分析软件Nvivo11 plus，从经济、政治、社会和文化四方面构建理论分析框架。为验证模型合理性，从全国28个省份获取到530份城市社区应急处置能力调查问卷，利用SPSS进行信度效度分析基础上，深入进行探索性和验证性因子分析，对模型构建的科学性进行验证。

ABSTRACT. 本文根据注意力经济理论，采用回归分析方法，基于哔哩哔哩平台视频数据，分析了社交媒体平台上网络视频的信息娱乐化对注意力经济的广度、深度、参与度和效度中的不同维度的影响。实证研究结果表明，信息娱乐化特征中，正面和负面的极端情感对注意力经济具有显著影响，内容故事化具有显著的积极影响，明星人物、软新闻主题和“标题党”具有显著的消极影响。从在线视频和媒体平台的角度，时长碎片化对注意力经济具有显著影响，呈现方式多样化、标签数量、权威媒体具有显著的积极影响，话题数量具有显著的消极影响。

ABSTRACT. A large number of players purchase superior virtual gear to increase their chances of winning a battle. However, the design of PvP games, particularly the design of the competitive balance among players, remains largely unexplored. We consider an optimal product line design problem that allows the developer to design the competitive balance. Results indicate that tournament design enables the developer to alleviate the well-known cannibalization effect caused by the release of free versions through multi-dimensional versioning, which renders the freemium strategy optimal for the game developer. Second, tournament design allows the developer to overcome players' budget constraints. Specifically, the developer can effectively monetize the participation of players who play the game for free by handicapping them through tournament design and charging the paying players a higher price. Counterintuitively, tournament design results in a Pareto improvement in the sense that it increases the developer's profits and benefits every player.

ABSTRACT. On mobile apps platforms, management responses enable developers to spotlight customer feedback and then react accordingly. Aiming to understand management responses in digital innovation, we develop a theoretical model of attention-allocation that addresses an underexplored but essential question: In a digital system, how is spotlighted customer feedback absorbed into the following innovation, and what role do management responses play in this absorption? To answer the questions, we first identify the spotlighted customer feedback, relevant management responses, and the subsequent mobile apps updates on the Apple iOS platform. Secondly, text mining algorithms are developed to analyze the feedback and responses, and then measure stimulus-driven attention, goal-oriented attention, and the knowledge absorption in subsequent updates. The empirical results reveal that responding to maintenance and functional customer feedback improves the subsequent knowledge absorption in mobile updates. Additionally, absorbing knowledge from customer feedback is also improved if developers customize and post actionable response.

ABSTRACT. 分析在线心理健康社区支持寻求者回帖可以识别问题未得到解决的帖子，可以精准为其提供帮助，从而可以帮助发帖者心理健康问题解决、促进在线心理健康社区发展。面向传统关键短语匹配以及词频统计识别心理认知改变出现较多遗漏以及准确度不高的问题，本研究从回帖的视角构建了一种融合表情情感信息与认知改变核心词信息的心理认知改变智能识别方法。模型首先基于规则匹配与人工标注针对表情情感信息进行编码，然后基于预训练词向量和相似度构建认知改变核心关键词词典。将编码后的表情情感词典和认知改变词典加入word2vec高维语义词向量训练中，使用训练好的模型将已标注认知改变识别文本转化为向量矩阵，再使用TextCNN在已标注的文本中训练分类器。与传统关键短语匹配以及词频统计相比，本研究构建的心理认知改变识别方法能较大的提升分类的准确度，更好的识别未发生认知改变以及发生认知改变的文本。本研究构建的框架可以为在线心理健康社区管理提供技术支撑，如为成员评价和影响力人物识别提供最直接的证据来源，辅助识别问题未得到解决的帖子，进而为帖子的推荐、心理健康问题的解决、成员的内容贡献与社区参与、社区的可持续发展提供有力支持。

ABSTRACT. 基于识别复杂关联和区分点击事件考虑应用内具体行为类型的需要，本文提出基于希尔伯特-施密特独立性指标得到行为类型间有向无环图骨架，再根据行为类型所属的移动应用配合错误发现率(FDR)控制等策略得到应用间关联的组有向无环图骨架算法。本研究基于真实数据设计了一套模拟数据生成机制，比较了新方法相比基于聚合数据的相关系数和有向无环图骨架方法的效果差异，结果显示新方法可以很好地考虑组内细粒度变量的信息，识别出原本被掩盖或忽视的关联。数据分析结果发现，应用品类间紧密关联程度差异大; 音乐、视频等品类内应用间关联更松散; 行为类型层面，消耗用户更多时间与金钱的深度行为间更容易产生相互促进或竞争效应。

ABSTRACT. 本文基于信号理论，从医生自我价值体现信息角度出发，揭示在线医疗平台上医生个人描述性信息丰富度和擅长信息特征对用户决策的影响。主要研究发现是：描述性信息包括医术水平、教育经历和社会影响力三个方面，不同描述性信息特征变量对患者决策影响不同，用户在选择医生时更多关注医术水平和社会影响力；擅长信息总量正向影响用户择医，进而用户在择医时会关注医生的擅长信息覆盖度，而医生擅长信息颗粒度对患者择医无明显影响。

ABSTRACT. 摘要：在线健康是结合了互联网和卫生服务行业的新兴领域，近年来，由于科技的发展和疫情等情况的出现，该领域的研究热点也在不断变化。本研究利用CiteSpace可视化工具对Web of Science数据库在2016-2020年间收录的在线健康主题的文献进行可视化分析，绘制出知识图谱，揭示该领域的研究热点和前沿，探讨未来发展趋势，为后续在线健康领域的相关研究提供参考。研究发现，健康焦虑、癌症、数字健康、初级医疗以及COVID-19等是近年在线健康领域的新兴研究点。

ABSTRACT. This paper seeks to investigate the predictive value of investors' intra-day social media discussions on firm risk. We conduct a textual analysis of user-generated content (UGC) to extract the volume (e.g., number of posts, comments, views) and valence (e.g., helpfulness, sentiment, opinion, topic dispersion) characteristics. Various predictive models based on machine learning methods are utilized to evaluate the predictive performance of UGC. The results indicate that both UGC valence and volume can provide additional predictive gains over the baseline model. More importantly, UGC valence can significantly outperform UGC volume in predicting firm risk. Besides, we find that UGC during the non-trading period of a day shows significantly better predictive performance as compared with UGC generated during the trading time. This suggests that social media discussions generated in the non-trading hours are more informative and value-relevant to investors, whereas there is excessive noise on social media during the trading hours.

ABSTRACT. The booming of online platforms has attracted academia’s increasing interest in cross-platform spillover of product consumption. This study investigates how physicians’ content creation in Tik Tok influences patients’ demands, comments and satisfaction towards the physicians on online health communities (OHCs). Using the difference-in-differences approach, we uncover asymmetric influences of cross-platform spillovers for high- and low-awareness physicians in Tik Tok. Specifically, low-awareness physicians do not enjoy the benefits (i.e., the increased volume of orders and comments on OHC) from content creation in Tik Tok, but their ratings turn to decline due to attention distraction caused by cross-platform activities. Conversely, for high-awareness physicians, we find a positive cross-platform spillover effect for orders and comments on OHC without decreasing their ratings. Despite the existence of attention distraction from cross-platform services for high-awareness physicians, the negative impact on feedbacks is offset by higher ratings from their cross-platform consumers.

ABSTRACT. Traditional machine learning methods have been widely applied to identify the determinants of depression in the elderly, while the lack of explainability of machine learning has been a long-standing limitation. Based on the 2018 China Health and Retirement Longitudinal Study, we combine the SHAP interpretation method with the LightGBM machine learning model to study the influencing factors of depression in the elderly. Results show that health status, socioeconomic status, family support, family structure, and social interaction are of key importance in identifying depression in the elderly. This study helps to demonstrate the effectiveness of SHAP in ranking influencing factors of depression in the elderly, and the results provide valuable practical insights in the prevention of depression in elderly.

ABSTRACT. The wide spread of misinformation on social media has caused huge threats to the physical and mental health of the public. It is of paramount importance to find effective intervention measures to reduce misinformation dissemination. We conducted a systematic literature review by analyzing 363 papers included in major academic databases. Our review is expected to (a) investigate the features of published research related to curbing the spread of misinformation on social media platforms, and (b) provide recommendations for future research on the topic.

ABSTRACT. Digital government is a new governance model that emerged in the era of advanced information technology. Providing public services is one of the government’s foundational capacities. This research aims to figure out key factors that may contribute to the varying levels of public service capacity of provincial governments in China. With the technology-organization-environment (TOE) framework, this research identifies five key influencing factors for the public service capacity of digital government. By using the qualitative comparative analysis method, this research figures out three solutions that can result in a high level of digital government public service capacity. The results suggest three typical development paths of digital government, including technology-economy driven provinces, platform-organization driven provinces, and organization-demand driven provinces. This research has implications for helping provincial governments to improve and allocate resources to advance their digital government public service capacities.

ABSTRACT. 数据交易是数据要素市场化配置的核心环节。针对数据需求者不能事前掌握被交易数据产品的质量、完整性和效用（即存在感知价值不确定），探究数据产品抽样策略，以提升数据需求者购买意愿是数据交易平台可持续运营过程中亟需解决的关键问题。本文构建双寡头竞争博弈模型，分别探究两个平台均不采取数据抽样策略、一个平台采取数据抽样策略和两个平台都采取数据抽样策略三种情景下的最优数据产品质量和交易价格。依据数据需求者对数据产品的需求偏好，将数据交易市场分为以数据匹配为主导和以数据质量为主导的两类数据交易市场，改进传统的Hotelling模型刻画数据抽样策略对数据需求者效用的影响，分析均衡状态下数据产品质量、平台的收益与平台数据抽样策略间关系。研究结论为数据交易平台采取数据抽样策略提供了理论指导，同时对改善平台的活跃度和数据交易量提供了新的实践路径。

ABSTRACT. 本文研究大数据环境下突发事件应急管理的技术赋能与使能价值，揭示突发事件应急管理技术赋能与使能价值创造之间的关系，以提升突发事件应急管理绩效。在使用文献计量学对相关领域文献进行元分析的基础上，首先界定突发事件应急管理技术赋能与使能价值创造的概念，阐述大数据环境下应急管理决策范式，进而构建突发事件智慧应急管理中从智慧应急基础“输入”到应急管理绩效提升“输出”的过程模型，并以地震灾害为例，对智慧应急的赋能与使能过程进行具体分析。本文通过探究突发事件应急管理从技术赋能到使能价值创造的过程，为优化突发事件智慧应急应用效果的研究提供了新视角。

ABSTRACT. Information technology has shown great potential in healthcare, especially in chronic disease management. In this paper, we leverage rational addiction model to investigate patients’ behavioral dynamic relationship in the context of IT-enabled diabetes self-management. We firstly build an analytical model to capture the impact of patients’ online learning behavior on their health outcome and the patients’ decision making about their self-management behaviors, then utilize a real-world data to empirically test the hypotheses. The GMM estimator of dynamic panel data model demonstrates the rational forward-looking behaviors generally exist in patients with diabetes, but they exhibit heterogeneous patterns depending on their demographics such as age, disease duration and gender. We contribute to the literature of IT-enabled chronic disease management, and also extend the application context of rational addiction model.

ABSTRACT. 保障“双碳”目标的顺利实现，应运数字化赋能低碳技术创新成为推进新发展理念的重要举措，更是实现文明跨越的创新抓手。基于“双碳”约束目标，构建以知识重构为中介变量、知识共享为调节变量的数字化转型驱动制造业低碳技术创新分析框架，实证探究数字化转型对低碳技术创新的影响。研究发现：制造业数字化转型对低碳技术创新产生显著正向影响，是推动低碳技术创新的重要动力来源；知识重构在数字化转型与低碳技术创新之间起到部分中介作用，发挥着关键桥梁作用；而知识共享对数字化转型与知识重构和低碳技术创新均起到正向调节作用。研究明晰了数字化赋能制造业低碳技术创新过程存在的差异性、适宜性，回答了数字经济时代如何有效利用知识管理实现数字化、帮助产业低碳创新升级问题，对引导产业绿色高质量发展具有重要参考意义。

ABSTRACT. Academic social networking sites provide a simple avenue for researchers to exchange information. However, the mechanism by which question-related characteristics affect the answer outcome in academic social Q&A (SQA) is still unclear. This study focuses on how different combinations of question-related characteristics affect answer outcomes in ResearchGate based on a configurational perspective. The study adopts fuzzy-set qualitative comparative analysis (fsQCA) to analyze complex causal relationships among variables of question-related characteristics and answer outcomes extracted from the log under the “Artificial Intelligence” topic in ResearchGate. The results show that, when questions contain a high degree of emotion and the questioner is often involved in SQA activities, even if the question text is not highly readable, they will receive high-quality answers; while questions with low answer quantity and quality are often difficult-to-read or from novice academics. In addition, the study proposed a particular pattern of communication in academic SQA: emotion-led communication.

ABSTRACT. 本文利用2012年至2016年间上市金融企业与投资者的网络互动数据，考察投资者关注度对股票收益率的影响以及由此带来的投资风险。本文分别以投资者对上市公司的关注次数、关注的细度以及情绪的积极程度作为代理变量来度量投资者关注。实证结果表明，对于证券、保险、信托、股份制与城商行四个金融子行业，这三类代理变量均为上市公司股票收益率的风险因子。但对于国有银行，这些现象并不显著。上市公司应充分利用风险因子产生的路径进行干预，借助专业信息平台，积极、全面地与市场沟通，加强自身业务的宣传和解读，提高信息透明性和市场有效性，降低股票波动风险。

ABSTRACT. Emotional chatbot is a kind of chat robot with the ability of emotional analysis and expression. At present, the technology of emotional chatbot is still in its infancy, and the academia lacks systematic and targeted theoretical re-search on the factors affecting the acceptance willingness of emotional chatbot. Based on the expanded valence the-oretical model, this paper takes users' perceived risk of emotional chatbot services and system quality defects as users' negative potency factors, human interaction, emotional competence and perceived pleasure as positive potency fac-tors, and personal innovation, efficiency expectation and self-efficacy as subjective psychological factors. We discuss the factors affecting users' behavior intentions of emotional chatbot, and takes gender, occupation, education level as adjustment variables to explore the differences of behavior intentions of different user groups for emotional chatbot. The research results provide suggestions for improving and promoting emotional chatbot, and lay a foundation for related research in the academia.

ABSTRACT. 数智化浪潮为人文学者数字学术研究和实践注入了新的动力，但与此同时学者们在与数字内容和技术交互中也面临数字囤积困境。本文采用半结构化访谈、关键事件技术法和主题分析法对人文学者的数字囤积行为进行了探究，包括对人文学者数字囤积行为的概念化解析、行为模式的动态演化特征及囤积者类型的识别、数字囤积情境因素的挖掘，并在此基础上构建多元要素和多情境方向发展的数字囤积行为形成机理模型。最后，从系统设计和技术赋能的实践视角出发，为提升信息系统对于解决人文学者数字囤积困境的赋能优势提供了参考。

ABSTRACT. 为捕捉更全面的用户偏好、景点特征及评级与在线评论的交互信息以解决数据稀疏和特征融合问题，论文提出了一种混合3D卷积融合评级和在线评论的景点推荐方法：首先采用深度矩阵分解和细粒度情感分析分别从评级和在线评论中提取用户和景点特征，其次通过特征堆叠实现交互后输入 3D 卷积网络提取非线性信号，然后利用相似度计算，为用户推荐排名前N的景点，最后采用去哪儿网数据集进行验证。结果表明，该方法具有较优的推荐性能。

ABSTRACT. Information asymmetry in online consultation is widespread in online health communities (OHCs). As a key quality signal, it is very important to solve the problem of information asymmetry between doctors and patients. Basis on social capital theory, combining the relevant concepts in knowledge management and signal transmission theory to construct a research model, this study aims to explain the deep-seated mechanism of how doctors' popular science works affect patients' online consultation intention. By adopting machine learning and natural language processing technology, a new variable representing "common language" was extracted from the unstructured data of 5927 popular science articles and 43624 online consultation records, and its influence mechanism on online consultation intention was investigated. It is found that the common language of doctors' popular science works has a positive impact on patients' online consultation intention through the mediation of cognitive trust. Moreover, the professional qualifications of doctors can significantly moderate the impact of popular science article trust on patients' willingness to online consultation. The results of this study extend the theoretical connotation and interpretation scope of social capital theory, and provide important reference for doctors to provide popular science knowledge and efficient operation of online medical communities.

ABSTRACT. Service robots are gradually being deployed to replace employees and provide certain services. However, service failures inevitably occur due to technology malfunctions and the nature of service. Appropriate design solutions to increase customer tolerance of service failures are vital for service platforms. Based on the computers as social actors paradigm, voice stereotypes, and social cognition theory, we conducted three scenario-based experiments to explore how the human-like voice types of service robots influenced customer tolerance of service failures. The results indicated that robots with adult female or child voices led to higher levels of customer tolerance than those with adult male voices. Also, warmth perceptions, rather than competence perceptions, fully mediated the effects of robot voice types. Furthermore, for robots with adult male voices, increasing the level of robot intelligence enhanced users’ warmth perceptions and diminished the difference between the warmth perceptions of different voices. These findings contribute to the literature on robot design for customer service and offer implications for practitioners regarding service robot design and deployment.

ABSTRACT. 本文基于感知价值与感知风险理论，探讨在线医美平台金钱或非金钱服务承诺对消费者购买意愿的影响及消费者冒险倾向、医美企业在线评分在该机制中的调节作用。通过2×2×2组间实验验证假设，研究发现：金钱与非金钱服务承诺对消费者购买意愿有不同程度的影响，相比于金钱补偿，非金钱服务承诺（即，免费术后修复）能显著提高消费者对医美服务的购买意愿；当冒险倾向或企业在线评分越低时，非金钱服务承诺对消费者购买意愿的正向影响更强。

ABSTRACT. 传统的问答社区专家推荐方法主要将问题的标题和内容看作一个整体来对专家的整体兴趣进行建模，忽略了专家会仅根据标题初步筛选感兴趣问题的事实。基于涉入理论，本文分析了问题的标题和内容在专家点击标题、回答问题决策中的不同作用，并提出了新的同时考虑点击和回答预测任务的专家推荐方法。本文利用心理健康问答平台“壹心理”的真实数据进行了实验，验证了本文方法针对传统的未分离标题和内容的各种推荐方法的优越性。

ABSTRACT. Background With the flourishment of e-health in recent years, e-consultations provided by doctors in Online Healthcare Communities (OHCs) are becoming more and more popular with the public in China. Meanwhile, proactive behaviors of doctors attribute to the success of OHCs, and they are often unsure how to behave proactively to attract patients, with limited research focusing on this. This study aims to explore how proactive behaviors of doctors affect their individual e-consultation service quantity in OHCs. Methods Data in our empirical analysis was collected from one representative OHC in China, referring to 3170 doctors in 865 medical teams. Hierarchical linear regression was conducted to examine the effects of doctors’ proactive behaviors at different levels on individual performance. Herein, proactive behaviors of doctors in OHCs mainly included response speed, pricing and related behaviors in the context of online medical teams. Results This study found that proactive behaviors at different level had significant impacts on individual Service Quantity (SQ) of e-consultations in OHCs. Further, positive effects could be verified in most conditions that were congruent with the logic of common sense, and the interaction terms demonstrated complex influences. Specifically, at the cross level, the switching cost weakened the relationship between price at individual level and individual SQ (β=-0.001, p<0.01), while strengthened the relationship between the response speed (β=0.110, p<0.01) at individual level and individual SQ. At the team level, the response speed in online medical teams positively moderated the effects of both price (β=0.438, p<0.01) and response speed (β=33.678, p<0.01) at individual level on individual SQ. In summary, proactive behaviors at different levels and their interaction effect play key roles in individual SQ. Conclusion Results of empirical analyses enable healthcare providers to adjust their behaviors proactively. In brief, our research provides healthcare practitioners with an improved understanding of the impacts of doctors’ proactive behaviors, and ultimately improve the efficiency and provision of delivered healthcare services in OHCs.

ABSTRACT. 信息市场是一种基于人群的预测工具，人机融合信息市场受益于人和机器互补的预测能力，提供更准确的预测结果。然而，市场中机器的身份披露可能会产生负面影响，机器亲社会行为的设计会减弱这种负面影响。本文研究机器收益分享设计对参与人活跃度（自愿参与预测任务的数量）的影响，具体关注收益分享的两个设计维度：人机交互目标结构（竞争、合作和无特定目标）和分配方式（按绩效分配和平均分配）。其中，前者表示机器的收益在什么条件或情况下分配，后者表示如何做收益分配。本文基于在线实验发现：第一，与人机合作目标结构相比，参与人在人群与机器竞争情境下活跃度更高。第二，引入机器分享收益设计后，参与人的活跃度降低。机器按绩效分配的收益分配方式会增加用户活跃度。第三，在人群与机器竞争的目标下，机器按绩效分配收益时用户活跃度更高。在人群与机器合作的目标场景中，机器平均分配其收益时参与人活跃度更高。除了上述三点关于收益分享设计对活跃度的影响，本文还发现在相对于人机竞争分享，人机合作时的感知机器威胁和感知机器能力更低，而感知机器温暖更高，结合人机合作分享时参与人活跃度低但决策质量高的结果，说明合作的人机交互目标改善了人机竞争交互带来的负面影响，营造了更有效的人机融合预测环境。本文的发现为人机融合预测中机器亲社会行为的设计提供了理论和实践贡献。

ABSTRACT. Deep synthesis can play a positive role in applications such as film production and virtual fitting. It also can generate ethical risks in malicious use such as defamation and fraud. Ethical risks cause public concern, but the concern is not evident in entertaining applications. Therefore, this study aims to understand the role of ethics and entertainment in the acceptance of deep synthesis applications. A mixed-method is used to qualitatively derive the ethical concerns and quantitatively validate the impact mechanism. We confirm that informed consent, privacy protection, traceability, and non-deception have significant impact on ethical acceptability and social acceptance, with privacy protection being the most sensitive. Perceived enjoyment significantly weakens the effect of ethical acceptability on social acceptance. The findings provide the entry point for ethical regulation of deep synthesis applications, and the weakening effect of perceived enjoyment is a wake-up call for regulators to guard against pan-entertainment applications.

ABSTRACT. As urban transportation commuting causes serious pollution problems, green commuting has aroused increased interest in academia. However, there is a lack of understanding of whether or not wealthy residents prefer green commuting and when residents choose green commuting. This study investigates how income (i.e., housing prices) affects residents’ green commuting choices. We integrate a novel data set to generate a unique dependent variable to evaluate residents’ green commuting rate, by combing two large real world transportation data sets. Our empirical analyses indicate a negative relationship between housing prices and green commuting. Additionally, residents’ green commuting choices differ across different commuting purposes. Specifically, the green commuting rate decreases for working, hospital visiting and hedonic purposes. This study contributes to the literature on urban traffic management by using real-world data to examine the factors affecting green commuting, while most of the research in this field is conducted using survey methods.

ABSTRACT. User-friendliness and intuitive interface fostered user participation in online health platforms. People know their health status anytime and anywhere and consult doctors online instead of going to physical hospitals. This study takes an online health platform as the research object, proposes and tests a model to explain users’ continuance intention to participate in online health communities through user engagement and perceived benefit, and tests the moderating effect of perceived vulnerability and perceived severity. The results show that the technology affordance characteristics of online health platforms affect users’ perceived benefit and online engagement, which further influence users’ continuance intention. Perceived vulnerability and perceived severity moderate the relationship between perceived benefits, online engagement and users’ continuance intention. This study has theoretical and practical implications for the online health discipline.

ABSTRACT. Cloud migration is a crucial step in enterprise digitalization. Enterprises migrate applications into the cloud for faster processing time, more access and lower energy consumption than deploying locally. However, the existing works do not consider the efficient utilization of cloud resources when maximizing the enterprises’ utility. In this paper, we propose a cross-layer cloud migration framework for efficiently allocating cloud resources to multiple competing enterprises. We divide the cloud migration system into two layers: enterprise layer and cloud layer. We introduce a Fisher market in economics to obtain optimal service allocation strategy and equilibrium price at the enterprise layer. In the cloud layer, we consider the optimal resource provisioning and formulate the problem as a convex function. Then, we propose a gradient-based algorithm for cross-layer resource allocation. Finally, we verify the effectiveness of the algorithm by simulation.

ABSTRACT. Based on the KMV model to assess credit risk , this paper explores the influence of senior executive changes on enterprise credit risk. On this basis, we can explore the adjustment effect of enterprise incentive mode and governance mode on this influence. The research results found that the credit risk of an enterprise increases significantly after the change of senior management, and the second position of senior management will strengthen the negative effect of senior executive change on the credit risk of enterprises, while the high concentration of equity of enterprises will weaken this negative effect. In addition, the research results found that both salary incentive and equity incentive can weaken the negative effect of senior executive changes on enterprise credit risk.

ABSTRACT. 本文通过Web of Science和中国知网数据库检索了2005年至2022年内的国内外关于人工智能服务代理(AISA)的拟人化影响消费者的86篇文献作为研究样本，对其进行了系统梳理。首先，本文回顾了AISA拟人化影响消费者的研究现状并总结了AISA拟人化的定义和类型。其次，本文构建了AISA拟人化影响消费者的研究框架。最后，本文提出未来研究应当关注AISA情感拟人化对消费者的影响、AISA拟人化带来的伦理和隐私问题、AISA拟人化对消费者福祉的影响、AISA拟人化在整个服务阶段中的动态变化机制、AISA拟人化影响消费者的其他应用情境等方向。

ABSTRACT. Physicians are the primary providers of online medical services, and their participation is critical to the vitality and sustainability of the online healthcare community. Drawing upon the affordances theory and job demands-resources model, we integrate required online effort and platform affordances in online work settings and propose a dual-path model of online retention for physicians. The expected findings are that physician, cognitive, and emotional labor discourage online retention of physicians, egocentric affordance, online collaboration affordances, and social presence affordances contribute to it, and job crafting mediates these effects. The expected findings may extend the understanding of the theoretical motivation behind continuance behavior and help platform managers to motivate physicians’ continued participation on the platforms.

ABSTRACT. Emerging research reveals the relationship between the Internet and public’s attitude towards healthcare. Some holds that Internet will improve their attitudes while others believe that it will deepen their misperceptions about healthcare. However, there is a lack of research that further disaggregates public attitudes into different dimensions and explores the different impacts of Internet use and Internet involvement. To answer this inconsistency, this study distinguished these two and divided the attitude toward healthcare into three aspects: doctor trust, medical institution satisfaction and medical problem perception. And this study used propensity score matching to analyze the effects of Internet on residents’ attitude by adopting the data from the China Family Panel study in 2018. The results show that Internet use only contributes to the rise of medical problem perception level. And Internet involvement increases Chinese residents’ doctor trust, but also ruined their medical institution satisfaction and exaggerated medical problem perception.

ABSTRACT. In order to fully realize the business value of cloud computing and achieve organizational objectives, it is extremely important to clarify the impact of different environmental characteristics on the ambidextrous innovation value of cloud computing. However, the existing literatures do not fully investigate the moderating role of environmental factors. This study conducts propensity score matching and difference-in-differences-in-differences analysis on the secondary hand performance panel data of 118 pairs of listed companies to investigated the moderating effect of the three environmental characteristics, namely dynamism, munificence and complexity, on the ambidextrous innovation value of cloud computing. The results show that cloud computing significantly promotes exploitative innovation in less dynamic environment and explorative innovation in high complex environments. Nevertheless, munificence explains a less significant proportion of the variance in ambidextrous innovation performance. This research creatively and empirically reveals the realization regularity of cloud computing ambidextrous innovation value under different environmental characteristics which provides theoretical and empirical implications for managers to carry out cloud based operation.

ABSTRACT. With the rapid development of online music platform, music socialization has become one of the mainstream online social forms. For the “effect of people with the same preference gathering together” characteristic of playlist comment section, this study adopts the uses and gratifications theory, technology acceptance model to construct a theoretical framework for the influence of users’ virtual social needs on the playlists’ selection behavior. In Study 1, Python technology was used to capture the playlist comment data. Based on the uses and gratifications approach, and the qualitative analysis method of grounded theory, five dimensions of users’ virtual social needs were obtained, namely, the memory resonance, emotional expression, entertainment, interaction and self-expression needs. Study 2 established an econometric regression model to verify the causal relationship between users’ virtual social needs and playlist selection behavior, using the number of plays, shares, and favorites as the evaluation indicators. The study found that users’ needs for entertainment, self-expression and emotional expression positively influence playlist sharing behavior; while the favoriting and playing behaviors are mainly positively affected by memory resonance and entertainment needs. Study 3 verified the causal mechanism between users’ social needs and the willingness to select playlists by constructing a structural equation model (SEM). Results showed that, different virtual social needs would further influence users’ willingness to play, share, and collect playlists by affecting the perceived usefulness, perceived ease of use, and perceived enjoyment, respectively. The purpose of this study is to reveal the users’ virtual social needs, behavioral patterns and influencing factors of music platforms, and to provide theoretical guidance for the recommendation strategy of high-quality playlists on music platforms.

ABSTRACT. 随着网络的普及和发展，越来越多人在社交媒体上讨论婚姻相关的社会关注的热点话题，比如彩礼的意义及必要性。然而，少有学者研究这种讨论对参与者的婚姻信任的影响。为填补这一研究空白，我们从微博上收集了与彩礼讨论相关的帖子。基于契约理论，我们构建了研究模型和假设，并采用计量模型检验了在线彩礼必要性的讨论行为和婚姻信任之间的影响机制。此外，我们也探索了自身的固有认知和他人的社会互动对主效应的调节作用。

ABSTRACT. The survival and development of listed enterprises are influenced by financing, and the financing risk assessment of listed enterprises is negatively affected by uncertainties of evaluation information caused by the difference of evaluation experts' experience. To address it, a financing risk assessment method of listed enterprises based on D-number theory improved analytic Hierarchy Process (D-AHP) and approximate ideal solution ranking method (TOPSIS) is proposed. The evaluation index system and hierarchical structure model are established according to the three financing methods of bond financing, equity financing and hybrid financing of listed financing risk. Then the D-AHP is used to solve the impact weight of each index, and the TOPSIS is used to calculate the expert weight. Finally, the financing risk value of listed enterprises is obtained, so as to give reasonable evaluation results about financing risk impact of listed enterprises.

ABSTRACT. 本文基于价值共创理论，以“好大夫在线”平台为案例识别共享医疗平台的各类行为，探讨主体在互动中扮演的角色，构建共享医疗平台价值共创过程模型，归纳价值维度，不仅能够提升双边市场用户体验和参与意愿，进而扩大市场规模；还能够促进资源交互与共享，使各方共创价值最大化。研究发现，需求方驱动供给方和平台方优化服务水平；平台方保障双边市场用户的利益；供给方为提升自身和平台的声誉、消费者体验做出贡献；共享医疗平台整体与社会双向嵌入，互促发展；各主体通过互动共创信息价值、功能价值、经济价值、社会价值。

Based on the value co-creation theory, this article takes “haodf.com” as a case, to construct a model of value co-creation process of sharing medical platform and inductive value dimensions, which can not only improve the experience and willingness to participate of users in two-sided market, thereby expand the market scale; but can also promote the interaction and sharing of resource, maximizing the value co-created by each subject. The results show that the consumer drives supplier and platform to optimize service levels; the platform guarantees the interests of two-sided market users; the supplier contributes to enhancing the reputation of himself or herself and the platform and improving the experience of consumer; the whole sharing medical platform is embedded in the society, promoting mutual development; the subjects co-create informational value, functional value, economic value, and social value through interactions.

ABSTRACT. Financial fraud has occurred from time to time and disrupts the normal operation of the market and hinders the healthy development of the accounting industry. To address this issue, the US Securities and Exchange Commission (SEC) initiates lawsuits against companies that violate accounting standards and published the records of these lawsuits on Accounting and Auditing Enforcement Releases (AAER). Researchers and practitioner from all kinds of area can then extract different information from it. However, at the moment, most information extraction algorithms depend on large human labor to define rules or mark tags for the training data, which is not feasible for this task. Our study proposes an end-to-end information extraction framework, the context-based one-shot information extraction system (COIES). Our experiment shows that the results of COIES approach human performance which requires only one example with the minimal prior knowledge input.

ABSTRACT. 本文基于不确定性降低理论，使用半结构式深度访谈法研究直播电商情境因素作用下在线评论对消费者退货意愿的影响，提出评论系统改进对策。研究表明：直播电商中消费者依然会阅读评论，但时间压力，群体压力和互动性分别通过降低信息处理能力，诱发从众效应和改变消费者的信息搜寻行为影响了在线评论降低产品不确定性方面的作用。直播电商平台可以通过弹幕展示可视化评论、增加评论搜索功能和定制化评论排序对评论系统进行改进。

ABSTRACT. 消费是推动经济增长的三驾马车之一，社会消费品零售总额是反映社会消费总需求的关键指标。然而，传统统计预测方法尚未达到对社会消费品零售总额预测的理想效果。为弥补传统预测变量及预测技术的不足，本文基于深度学习长期和短期时间序列网络(LSTNet)，结合网络搜索数据与政府统计数据，构建LSTNet&BI模型开展浙江省及地级市社会消费品零售总额的预测研究，同时考虑多种基准预测模型进行对比分析。研究发现：(1)引入网络搜索数据能够有效提高LSTNet模型的预测性能与预测精度；(2) LSTNet&BI模型具有较好的泛化能力，对浙江省社会消费品零售总额的短期和长期预测效果都较稳定，其预测性能与预测精度均优于其余五种基准模型(LSTNet、LSTM&BI、SVR&BI、XGB&BI和ARIMA)；(3) LSTNet&BI模型具备较强的稳健性，其对杭州市、绍兴市和衢州市社会消费品零售总额的预测效果也较好。研究结果表明LSTNet&BI模型具有一定的实用价值，该方法为社会消费品零售总额预测提供了一种新思路，丰富了机器学习在宏观经济指标预测领域的应用研究。

ABSTRACT. 在线下影院遭受疫情冲击的当下，流媒体平台中的电影作品开始获得越来越多消费者的青睐，电影制作商、流媒体平台管理者也亟需理解消费者的电影偏好在线下、线上观看渠道中的差异。对此，本文以2011-2020年我国2122部院线电影为样本，分析流媒体平台相较于线下影院的消费者偏好变化，并探究两个渠道中电影份额分布的差异。研究结果表明：相对于线下影院，在流媒体平台上风格轻快的电影会获得更多观看，而演员和导演号召力的作用下降；此外，流媒体平台上的电影份额分布呈现出更明显的长尾现象，这一结果证实了长尾理论在数字内容产品中的适用性。

ABSTRACT. 产品累积的在线评论内容是支撑消费者决策的重要信息来源，以往基于评论动机及评论有用性的产品在线评论生成机制研究忽视了消费者决策过程中不同阶段的信息价值。本文基于预测用户生成内容受欢迎程度的替代因素：内容新颖性，定义了评论内容新颖性；分析讨论消费者在决策过程中获取的产品公共信息、产品体验信息对评论内容新颖性的影响机制，明确了评论内容生成的信息来源。本文基于2007年至2012年消费者在京东商城发布的1,566,220条评论数据进行了实证分析，研究结果表明消费者获取的产品体验信息量正向影响消费者评论中不同于其已知公开信息的部分（即评论内容新颖性）。消费者对产品公共信息的了解程度负向调节产品体验信息量对评论内容新颖性的正向影响。且上述关系受到暴露新属性、暴露新观点的机制的交替影响。研究结果为商家和平台优化产品评论中产品信息的曝光程度提供重要管理启示。

ABSTRACT. The market performance of mobile apps is very important to developers, but it is difficult to maintain or improve in the highly competitive market. An essential method to achieve the competitive advantage is iterative and incremental to update the apps. We propose a dynamic approach to capture the update strategy of mobile apps. Specifically, Hidden Markov Models are built to examine the relationships among update strategy, user satisfaction, and app performance. Theoretically, we propose that the update strategy determines the transmission between various levels of user satisfaction, which is the hidden states in HMM. Then, the transmission of user satisfaction results in app performance. The critical contribution of our study is that the dynamic process of mobile apps updates is theoretically and empirically examined. In this RIP, we propose the research design and discuss the implications.

ABSTRACT. 本研究以心理健康咨询为场景，采用情景模拟实验法，探究社交聊天机器人虚拟形象的三种呈现方式（简单文本式、头像式和背景式）对用户自我披露意愿和行为的影响，并检验了社会存在感、私人自我意识和公众自我意识的中介效应。研究表明，背景式虚拟形象呈现方式对自我披露意愿有显著抑制作用，简单文本式和头像式虚拟形象呈现方式没有显著差异。同时，研究发现社会存在感和私人自我意识是两个有效的中介变量。

ABSTRACT. 跨组织信息系统（IOIS）产生并支持跨组织协作关系，临近度被视为跨组织关系的重要影响因素，但已有研究尚未对其影响机制达成一致结论。本文基于复杂网络方法进行实证分析，探究IOIS中临近度对跨组织协作关系的影响机制并识别三项调节作用。结果表明：IOIS中，临近度对跨组织协作关系具有“倒U型”的非线性影响；地理距离、结构型社会资本与关系型社会资本显著调节倒U关系并降低最佳临近度水平；两种社会资本均正向影响跨组织协作关系。

ABSTRACT. This study explores the influence of three specific community-based mechanisms on trust and transaction intention from three dimensions of relational governance (relationship norms, conflict resolution and mutual dependence). At the same time, this study compares the differences effect between consumers and prosumers. Taking the second-hand trading platform Xianyu as an example, structural equation model was used to analyze the data based on 721 valid questionnaires. The results show that interest group, feedback mechanism and dispute resolution mechanism all have significant positive effects on seller trust. In addition, the impact of dispute resolution mechanism on trust in seller is higher for prosumers than for consumers. Current research focuses on the impact of social attributes of community on users, this study explores different specific community-based mechanisms. This study extends the previous research on community-based governance, explores the boundary conditions of community-based governance.

ABSTRACT. Based on the relevant literature on the elaboration likelihood model and vicarious learning theory, this study investigates the impacts of the danmaku sent by co-viewers on consumers’ purchase intention in E-commerce live streaming. An online experiment was designed and conducted to examine the effects of danmku on consumer behavior in a simulated E-commerce live streaming setting. It is found that the accuracy and consistency of danmaku sent by co-viewers increases consumers’ purchase intention by improving consumers’ vicarious learning. Meanwhile, the credibility of danmaku affects consumers’ purchase intention via eliciting consumers’ resonance. Also, the findings show that age has a moderating effect on the impacts of vicarious learning and resonance on consumers’ purchase intention.

ABSTRACT. With increasing online review manipulation on various transactional platforms, a new merchant manipulation strategy arises – manipulating the reviews by inducing consumers to praise employees’ names in reviews and give high ratings. To explore the effect of this new manipulation strategy on eWOM, this study constructs machine learning models for average rating and rating distribution prediction, using review text related features and name-related feature reflecting the manipulation. Our results indicate that the manipulation of reviews does improve average rating of merchants but leads to sharper J-shaped distribution and low-quality reviews, which will reduce reference value and reliability of reviews, further weakening the positive impact of average rating.

ABSTRACT. 制造业采购经理人指数（Purchasing Managers’ Index ，PMI）是反映国家经济运行情况的重要指标，而传统预测模型对该类时序数据预测精度不高。针对制造业PMI指数的非线性、波动性和数据量少的特点，提出一种基于一维离散小波变换进行数据预处理的组合模型，时序数据经过小波变换，由整合移动平均自回归-广义自回归条件异方差模型（Auto Regressive Moving Average-Generalized Autoregressive Conditional Heteroscedasticity，ARMA-GARCH）处理稳态低频数据，门控循环单元（gated recurrent unit，GRU）处理波动性强的高频数据，将各频段预测结果进行融合得到最终预测结果。为验证模型有效性，选取一定数据量的PMI指数进行实验，结果表明，与其他常见模型对比，本文构建的组合模型具有较好的预测精度与性能，平均绝对误差（MAE）、均方根误差（RMSE）、平均绝对百分比误差（MAPE）分别达到0.00329、0.004162，0.65%。

ABSTRACT. 以往的研究发现美观度可以影响消费者和投资者的选择偏好和价值判断。然而，现有的文献一方面仅关注具体的美学元素（如图片、颜色、字体和图文比例等），缺乏对美观度这一更加全局和抽象概念的衡量；另一方面主要围绕对公司感知形象的影响，缺乏针对公司实际经济利益的定量结论。本文以2007-2019年发布社会责任报告的上市公司为研究对象，首次采用深度学习方法提取社会责任报告中的美观度指标，并考察了社会责任报告美观度与上市公司债务融资成本的经验影响关系。结果发现：上市公司的社会责任报告美观度越高，其债务融资成本越低，意味着更美观的社会责任报告能够更有效地向债权人传递企业履行社会责任和披露信息的积极信号，降低债权人对不确定性的评估，增强债权人对企业还贷的信心。社会责任报告美观度对债务融资成本的抑制作用对分析师关注度高和机构投资者持股比例高的企业更加显著。此外，进一步的分析表明，媒体关注度同样会增强社会责任报告美观度对债务融资成本的抑制作用。本研究不仅从技术增强视角探索了深度学习方法对企业社会责任报告研究的作用，也为公司披露社会责任信息和制作社会责任报告提供了有益的启示。

ABSTRACT. 为了衡量供应商能否持续改进技术水平，保障供应链的安全运作，本研究基于多种来源的数据对企业的技术创新能力进行评估，构建了分类评估框架和技术创新风险评价指标体系。为验证所构建指标体系的有效性，本研究选取某集团的143家不同规模和类型的供应商为样本，使用层次聚类法、熵权赋值法、文本挖掘方法等研究方法，通过构建包含技术能力、人力资本与研发条件3个核心维度，19个关键指标的指标体系，评估供应商的创新能力。针对其中68家重要供应商，模型测算结果与专家打分相关性为0.58，总体一致性较高，在评估上千家供应商的技术创新风险时有一定优势。

ABSTRACT. Due to the large amount of inaccurate information online, the public can be particularly vulnerable to misinformation. This study aims to fuse Knowledge Graph and Artificial Neural Network (KGANN) to detect online health misinformation. Our model transforms a public medical knowledge graph into a neural network so that the knowledge graph can be trained by backpropagation algorithm. The model integrates medical knowledge and feature vectors, and determines their weights during training. We performed KGANN on two public disease-specific datasets (including factual and error information related to diabetes and cancer) to validate its effectiveness. The experimental results show that KGANN significantly outperforms two competing methods in terms of F1 Score and Accuracy, and the operation process of the model can be explained to a certain extent through triples in the knowledge graph.

ABSTRACT. 数字平台连接供需两端使得交易在线化，提高市场效率的同时也放大了平台产品的质量与服务问题，平台中的用户投诉数量居高不下。投诉会损害供给端的声誉并可能影响其在平台中的曝光率，进而影响其长期发展，最终不利于平台经济健康发展。因此，本文认为用户投诉会对平台供给端产生影响，包括提高服务水平和增加商品发布数量。基于此，本研究以中国某租房平台为研究情境，关注用户投诉行为，使用双重差分法（DID）检验用户投诉对平台供给端所产生的具体影响。实证结果支持如下结论：（1）用户投诉会导致平台供给端提高服务水平，但不会明显增加房源发布数量；（2）房源相对价格越高，受投诉的平台供给端的服务水平提升越有限，新增房源数越少；（3）所处商圈竞争压力越大，受投诉的平台供给端不会明显提高服务水平，但新增房源数越多。

ABSTRACT. Air pollution is a major issue related to the national economy and the people's livelihood. At present, the research on air pollution emissions mostly focuses on analysis in a specific industry or regions. Enterprise is the most important entity unit of air pollution source. While limited by the amount and granularity of data, there are a few studies on air pollution of industrial enterprises. Especially, there is a lack of research on anomaly of enterprises, the relationships between districts or counties, and between pollutants emitted by enterprises and industries of enterprises. For this purpose, driven by big data of air pollution emissions of enterprises in Beijing-Tianjin-Hebei, the data mining of enterprises’ pollution emissions is carried out, including the outlier detection based on clustering, association rule mining based on Apriori and association degree discovery based on grey association analysis. The results show that: (1) In Beijing-Tianjin-Hebei, industrial enterprises can be divided into six clusters, of which three categories belongs to outliers, which have excessive emissions of total VOCs, PM and NH3 respectively; (2) From the perspective of the association between different data, these districts nearby Hengshui and Shijiazhuang city in Hebei province form strong association rules. (3)From the perspective of the association between different features, the industries affecting NOx and SO2 mainly are electric power, heat production and supply industry, metal smelting and processing industries.

ABSTRACT. 数智化新跃迁时代，随着人工智能教育的发展，机器人有望成为教师，有效解决教育资源短缺和不均衡的问题。现有对教育机器人接受度的研究只考虑了其智能性和有效性，然而教育不能只注重效率和智能。通过编码学生对教育机器人的接受动因和结构方程验证，结果发现，学生对教育机器人的智能性认可度较高，除有效性外影响学生接受的动因还包括技术相关因素：安全性，情感相关因素：融洽性、外观设计和有趣性，环境相关因素：社会影响。学生拥抱教育机器人的智能性和有趣性，却又因其有效性不足、缺乏情感支持和监管而止步。推动教育机器人的落地需要重视教学设计，关注情感支持，加强监管规范，鼓励人机协同教学。本研究为社交机器人的技术接收度模型提供了新因素——融洽性。

ABSTRACT. 用户主要通过文本的方式为平台贡献创意，创意语言风格传达了重要信息，本研究关注文本语言风格对创意扩散度的影响。爬取典型开放式创新平台Thingiverse的数据，使用文本挖掘方法识别创意文本语言风格，探索创意文本语言风格对创意扩散度的影响，并使用机器学习算法对创意扩散度进行预测。结果表明，四种语言风格包括逻辑诉诸、人格诉诸、情感诉诸和信息熵均对创意扩散度产生正向影响，且创意认可度中介了语言风格对创意扩散度的影响。

ABSTRACT. Public crisis management is an important part of social governance modernization. The new era has put forward new requirements for social governance. We need to change the concept of governance, build a governance system, and improve the level of governance. The development of fuzzy decision making method further promotes the scientific management of public crisis events. Facing complex and changeable decision making problems in real life, decision makers evaluate and quantify various decisions based on expert index system. They evaluate and rank options through a series of methods to produce scientific and reasonable results. In this paper, we propose a new q-rung orthopair fuzzy number (q-ROFN) ranking method based on the analysis of the existing q-ROFN ranking methods, and apply this new proposal in the TOMID decision making method. The purpose of this paper is to make a selection of public crisis events management scheme by the method of the expanded TODIM decision making.

ABSTRACT. The COVID-19 has had a severe impact on global health and the economy. Policy interventions conducted by the government play an essential role in curbing the spread of the COVID-19. In this study, we propose a policy support system based on deep reinforcement learning (DRL), to provide scenarios of artificial intelligent practices for crisis management. The preliminary results show that the proposed system outperforms the benchmark metrics and policy implementations in the real world significantly, regarding the infection rate and normalized discounted cumulative economic gain from a long-term view.

ABSTRACT. Blockchain has been touted as a game changer in supply chains. While the technology can greatly improve the overall supply chain management, there are ethical challenges, and its ethical nature fundamentally implicates issues associated with sustainable development goals (SDGs). We are therefore yet to know the underlying ethical dilemmas as well as how to navigate the varied ethical complexities while creating value through blockchain-powered supply chains. Using the theoretical lens of normative ethics, this study detects various ethical complexities faced by blockchain in a developing country. The study identifies four types of ethical challenges, and proposes a proper balance between four types of ethical dualisms: balancing design efficiency with ease of use, balancing transparency with privacy, balancing open sharing with adequate data protection, and balancing user concerns with environmental concerns. The study offers rich contextual insights for developing countries and emerging markets, and has both theoretical and practical implications.

ABSTRACT. 问答社区内促进问题浏览向回答的流量转化至关重要。以知乎的2085条问题为样本，应用模糊集定性比较分析，从注意力分配视角对问答社区的流量转化进行组态研究。研究发现：高流量转化率问题的组态路径包括低竞争-强从众刺激与低竞争-高提问者度中心性刺激的简洁型问题，与中/低流量转化率问题的组态路径并非完全因果对称；知识结构化程度不同的问题实现流量转化的组态存在差异。结论有助于促进平台流量转化，优化问答界面设计。

ABSTRACT. 在线问答社区的持续发展取决于用户的持续知识贡献。然而，用户的知识贡献行为并非一成不变。本研究利用潜类别增长模型对在社区用户的知识贡献行为进行分析，刻画用户知识贡献行为的发展轨迹，并根据发展轨迹的异质性识别社区中不同类型的用户。研究结果有助于管理者了解问答社区中不同类型用户的特点，更有针对性地采取措施促进用户持续贡献知识。

ABSTRACT. The pervasiveness of multiple types of digital footprints recorded on e-commerce platforms have added fuel to the design of personalized recommender systems. Despite the abundance, consumers’ digital footprints can be confounded with many causes, both internally and externally. To disentangle the causes driving consumers’ behaviors, a causal recommendation method, i.e., DIPC, based on cause disentanglement at various consumption stages is proposed in the paper. Referring to related theories, interest and item popularity are recognized as causes driving consumer behaviors in the need recognition stage, while behaviors in the pre-purchase and purchase stages are assumed to be motivated by interest and conformity. To rigorously evaluate the performance of DIPC, extensive experiments are conducted on a real-world dataset with carefully designed protocol in terms of modeling multiple digital footprints and causality learning. The results show that DIPC outperforms all baselines significantly and possesses good interpretability, demonstrating the superiority of the proposed causal recommendation method.

ABSTRACT. 数字支付在数字经济中扮演着重要角色。本文采用系统性综述法分析数字支付领域用户使用意愿对实际行为的解释和预测情况。通过在Web of Science数据库进行关键词搜索并根据纳入标准进行筛选，最终锚定了18个数字支付研究。本研究发现使用意愿与行为之间存在较大差异，这说明使用意愿对行为的预测与解释是不充分的。本研究进一步分析了这种差异产生的4种原因。揭示数字支付领域用户使用意愿对行为解释不足的现象对研究者具有一定启示性价值。

ABSTRACT. 本文研究了公众关注对分析师访问的影响。为了建立因果关系，本文使用胡润百富榜作为外生冲击来识别公众关注的变化，使用双重差分法，本文发现公众关注显著提高了分析师对上榜公司的访问数量。这种关系在信息环境复杂的公司、股票收益波动较大的公司以及非国有上市公司中更为明显,表明公众关注对分析师访问量的正向影响是通过投资者对分析师服务的需求这一渠道实现的。进一步分析表明，分析师对公司的访问提高了分析师盈余预测的准确度。本文结果强调了公众关注对企业信息环境的重要性。

ABSTRACT. This paper examines the impact of information technology investment on the high quality development of enterprises, taking the A-share listed companies in China from 2010 to 2020 as the research object. Further mechanism tests show that corporate innovation and human capital play a mediating role in the relationship between information technology investment and high-quality corporate development, i.e., corporate information technology investment promotes corporate innovation and optimizes human capital structure, which in turn promotes high-quality corporate development.

ABSTRACT. Social media is used as a front for online mapping of offline public opinion on public health emergencies, and multimodal information with images and texts becomes the main way of public sentiment expression. To make full use of the relevance and complementarity among different modalities and improve the accuracy of multimodal negative sentiment recognition of online public opinion for public health emergencies, we construct a two-stage, hybrid fusion strategy-driven multimodal fine-grained negative sentiment recognition model (THFMFNSR). This model comprises BERT and ViT-based multimodal feature representation, GCN-based feature fusion, multiple classifiers, and rule-based decision fusion. By collecting image-text data about COVID-19 from Sina Weibo, this paper verifies the effectiveness of the model and extracts the best sentiment decision fusion rules and classifier configurations. The results show that compared with the optimal sentiment recognition model with text, image, and image-text feature fusion, the accuracy of this model in sentiment recognition and fine-grained negative sentiment recognition is improved.

ABSTRACT. 智慧选品是新零售的核心环节之一，但是现有工作严重依赖人工经验。即使少数研究提出了机器学习辅助方法，但结果的可解释性较差。为此本文致力于提出兼具预测精度与可解释性的基于SHAP模型的选品经验挖掘框架，并基于大型连锁零售超市609件商品的44万余条真实销量数据，检验了该选品经验挖掘框架的预测精度，提取了核心选品经验。该研究对于拓展智慧选品可解释性AI研究方法以及零售企业智慧选品实践具有重要的理论和现实意义。

ABSTRACT. 在信息产品营销中，企业既可通过提供奖励，鼓励用户向潜在用户进行推荐，又可通过功 能研发，增加产品的内生网络外部性。本文基于一对一推广的博弈论模型，研究企业如何在产品端 的“病毒性设计”和市场端的“奖励推荐”策略之间进行平衡。结论表明，产品的病毒性设计与推 荐奖励策略之间存在复杂的联系:奖励分配方式由产品与市场特征决定;在奖励推荐人时，产品策 略和营销策略相对独立;而当奖励被推荐人时，二者存在替代关系。

ABSTRACT. We examine the effect of social capital on participant retention in online mental health community, and disentangle the effect of bridging and bonding social capital on participant retention in this paper. Specifically, we derive participant profile data and activity data for 15 years from a Chinese online mental health community and construct social networks based on reply relationship for every half year. Following prior studies, bridging social capital and bonding social capital are measured by structural holes and network closure respectively. We conduct survival analysis to examine whether social capital has effect on participant retention, and use panel Logit model to capture the efficacy of different types of social capital. Results show that social capital significantly improves participant retention rate; bridging social capital has positive effect on participant retention, whereas bonding social capital has negative effect on participant retention

ABSTRACT. Though online retailers have put much efforts to optimize product image to attract consumers and increase revenue, studies about how specific image features promote product sales are rare. This study aims to examine whether image features have impact on product sales, and identify a set of key features essential to promote product sales. Specifically, we collected product images and corresponding sales data from one of the leading online food delivery platform in China. We used image processing technology to obtain image global features and regional features, and conducted a cross-sectional analysis and a difference-in-difference-in-differences framework to examine the effect of image features on sales. Results show that image saturation, colorfulness and the difference of contrast between foreground and background positively influence product sales, while image contrast has negative effect on sales. This study sheds light on the effect of image features and provides practical implications for product presentation

ABSTRACT. 新能源政策是我国国家长期战略政策，具有随时间变迁、地域差异和多主体协同制定三个特征，对这三个方面开展研究有助于深入认识我国新能源政策制定的规律和实现政策智能。本文基于2011年1月至2022年1月期间，由中央、各部委以及各省区颁发的共计1937份新能源政策文本，采用文本挖掘和共现网络分析方法，从政策的发布时间、发布地域和发文主体三个维度对新能源政策进行分析，揭示我国新能源政策的时空演化规律和发文主体协同特征。

ABSTRACT. 为了探究国际联合资助与国际合作发文间的网络演化关联关系，本文根据WoS数据库SCIE核心集中2009-2018年的论文数据构建国际联合资助网络和国际合作发文网络，使用QAP、ERGM和TERGM方法进行分析。研究发现，国际联合资助网络与国际合作发文网络具有较强的关联性；处于中心位置的资助机构与科研机构在网络演化中更容易形成新的合作关系；一个节点在国际合作发文网络中处于高度闭合的聚类中时，在资助网络中同样难以形成新的合作关系等结论。

ABSTRACT. Aiming at the heterogeneity of needs of various participants in the process of emergency rescue. In the process of multi cycle emergency material scheduling, the disaster satisfaction and government satisfaction are defined, and the multi cycle scheduling model of emergency materials aiming at the maximum comprehensive satisfaction is constructed. A random leapfrog algorithm based on reverse learning mechanism is designed to solve the model. The reverse learning mechanism and genetic crossover operator are embedded in the random leapfrog algorithm to improve the search ability of the algorithm. The superiority of the proposed algorithm is proved by four test functions, and the model is verified by an example. The example results show that the solution accuracy of the proposed algorithm is better than that of random leapfrog algorithm and genetic algorithm.

ABSTRACT. 本文通过对社交媒体投资平台上的投资者评论进行文本分析和有监督机器学习，量化出一个投资者情绪，并通过数据爬取构建了投资者意见分歧的指标，研究了投资者情绪对股票流动性的影响，结果表明，投资者情绪对于股票流动性存在显著的正向影响。除此之外，我们还验证了投资者情绪对于意见分歧的正向促进作用，以及意见分歧在投资者情绪影响股票流动性过程中起到的部分中介作用。稳健性检验表明结果是可靠的。

ABSTRACT. 本文从企业层面以121支碳中和概念股为研究对象，旨在研究媒体关注度对概念股股票异常收益率的影响及投资者情绪的调节作用。并在此基础上进一步研究投资者情绪的不对称作用。实证结果表明，碳中和媒体关注度与碳中和概念股股票异常收益之间呈显著正相关关系，投资者情绪具有显著调节作用。此外，当投资者情绪高涨时，媒体关注度对股票异常收益有显著影响，而情绪低落时影响并不显著。

ABSTRACT. Although AI-based chatbots have burgeoned in multiple business practices and demonstrated emerging potential in emotional support, little knowledge about the mechanism underlying the relationship between AI-based relational chatbots’ anthropomorphic attributes and user engagement. Drawing from the social judgment theory, we integrated agentic-style and communal-style to build relational chatbots’ conversational styles and proposed that emotional judgement mediated the relationship between conversational styles and user engagement with relational chatbots. Two types of AI avatars (humanlike vs. cartoonlike) are employed to examine the possible boundary effect of the above relationship. Two studies involving several online and lab experiments are planned to conduct to examine our hypotheses further. It is expected that we could extend the existing theories involving social judgment theory and human reactivity to AI-based chatbots in the setting of emotional care, and identify the potential joint effects of different types of anthropomorphic attributes of AI-based relational chatbots on user behaviors.

ABSTRACT. 本文采用经济学建模方法，探究在双寡头竞争市场下，企业利用从数据供应商购买的数据来为用户提供个性化 产品的策略，给出了企业的数据购买策略，产品定价策略以及市场均衡。研究的结果表明:在均衡时，数据供应商会 将数据同时卖给两家企业。但相互竞争的企业也都会采用个性化定价的方式，最终导致了基于数据的产品个性化加剧 企业的价格竞争，降低企业利润，但增加了消费者剩余和社会福利。

ABSTRACT. We aim to explore how listings owned by a multi-listing host affect each other, and the spillover effects of other listings’ online reviews on focal listing. Using a unique dataset of 1478 listings managed by 542 hosts ranging from October 2012 to June 2019 on Xiaozhu.com, we constructed two empirical models to examine the main effect of the number of other listings owned by the same host and the moderating effect of other listings’ online review on the focal listing performance, i.e., date difference between listing’s first sales and online date, and listing’s monthly sales. The results show that the number of other listings owned by the same host negatively affects listing performances, and online reviews have positive spillover effects. Our research contributes to both the home-sharing and spillover effect of online review literature and has substantial implications for the operators of home-sharing platform and multi-listing hosts on the platform.

ABSTRACT. After service failure, the occurrence of chatbots often brings bad service experiences to people. In order to improve consumer satisfaction when interacting with chatbots in service recovery, we design an online experiment to explore appropriate communication style designs for chatbots, also considering the moderating effects of consumers’ relationship orientation and task complexity. Results show that during service recovery, consumers are more satisfied with social-oriented chatbots rather than task-oriented ones. Besides, we explore the mechanism by which the communication style affects consumer satisfaction in service recovery by introducing cognition-based trust and affect-based trust as mediating variables.

ABSTRACT. 疫情防控常态化使得老年人缺乏陪伴与关怀，短视频迅速融入老年人的生活。然而老年人对时间概念认知的特殊意义如何影响其短视频持续使用行为仍缺乏关注。本文基于社会情绪选择理论和沉浸理论，将开放未来时间观、现在享乐主义时间观、沉浸体验、情感承诺、短视频类型等作为研究变量，构建老年人持续使用短视频APP的概念模型，以期丰富老年人信息系统使用决策和成功老龄化领域相关研究，为老年人信息系统行为提供理论支持和战略参考。

ABSTRACT. 缺血性脑卒中作为一种常见的急性脑血管疾病，是导致成人死亡和致残的重要原因。本研究旨在利用基于多源数据融合的机器学习算法，预测缺血性脑卒中患者的临床药物治疗风险。通过融合国际脑卒中试验数据集，对比随机森林、Logistic回归和梯度提升决策树算法的预测效果。其中，梯度提升决策树的召回率达到91.6%，AUC为0.832，效果最佳。实验结果表明，基于多源数据融合的机器学习算法在缺血性脑卒中药物治疗风险预测中具有较好的适用性。

ABSTRACT. 对消费者购买行为及其内在机理展开深入研究，能帮助企业及营销人员更有效的了解消费者需求，实施营销计划，完成企业目标，实现企业愿景。目前关于在线视频广告的广告效果研究，许多学者将目光聚焦于广告和视频的相关度，包括广告产品和视频主题的相关度，广告类型和视频类型的相关度，广告音乐和视频音乐的相关度等。研究发现，广告相关度对消费者的品牌态度和购买意愿会产生积极影响。但大多数都是采用传统测度的行为学实验进行研究的，也就意味着它无法揭示消费者在观看不同相关度的广告时，大脑对广告信息的认知加工过程。本文探讨在线视频广告在内容方面的相关度对消费者品牌态度的影响，以及他们如何受到情绪、加工流畅性和说服知识的影响。通过结合使用功能性磁共振成像技术和问卷调研法，本文得出以下结论： （1）广告-视频的内容相关性会影响消费者对广告中出现商品的品牌态度。相关性程度越高，品牌态度越好； （2）广告-视频的内容相关性会影响消费者对广告的情绪，进而影响对广告中出现商品的品牌态度。相关性程度越高，情绪越积极，品牌态度越好； （3）广告-视频的内容相关性会影响消费者对广告信息的加工程度，进而影响对广告中出现商品的品牌态度。相关性程度越高，信息加工流畅性越好，品牌态度越好； （4）广告-视频的内容相关性会影响消费者大脑杏仁核和纹状体ALFF的激活。相关性程度越高，激活越强烈。 （5）加工流畅性和杏仁核激活情况存在显著正相关关系，加工流畅性越高，杏仁核激活强度越大。 （6）随着视频播放，消费者进入视频情境，杏仁核ALFF激活程度逐步降低。 本研究在理论层面，不仅从管理学角度解释视频-广告的内容相关度为什么会影响消费者的品牌态度和购买意愿；而且从神经角度探寻广告相关度对消费者购买意愿影响背后的神经机制，丰富国内学者对在线视频广告效果的研究。最后，在现实层面，可以给企业的广告的内容制作和投放策略提供理论支撑和建议。

ABSTRACT. 智能问诊聊天机器人提供了一种专业化、即时响应、低成本的健康信息咨询工具。本文从功能、社会、用户动机三个特征维度，构建在线智能问诊聊天机器人用户采纳前因组配模型。采用fsQCA和访谈相结合的混合研究方法，通过收集347名用户的调查问卷数据进行模糊集定性比较分析，并与后续12位半结构化访谈结果相结合。研究结果共发现了五种因果组配方案，感知社会存在是核心条件。本研究为健康服务机器人的开发者和制造商提供了实践指导。

ABSTRACT. 随着在线社交推介逐步成为社交电商营销主要模式之一，多任务社交推荐系统设计对驱动用户参与社交分享的影响，成为电子商务界研究的重要议题。本文以社会交换理论为基础，采用实验分析方法，重点探究了多任务社交推介情境下，商家推介系统信息框架设计和分享机制对用户参与意愿的影响。研究发现：在多任务社交推介场景下，相对于任务导向信息框架设计，奖励导向的信息框架设计更有利于用户参与推介活动。

ABSTRACT. 日益增加的版权成本使得数字内容平台迫切需要对作品的用户留存能力进行进行更准确的评价，但由于内 容平台大多采用聚合订阅，导致单个内容的评价非常困难。本文结合某内容平台的真实数据，通过构建用户访问 的轨迹网络，得到作品的留存贡献分数及相应排名并开展留存预测，利用 XGBoost 模型结合可解释性机器学习领 域的 SHAP 方法揭示了特征与留存、特征与特征之间的非线性作用，相关结果对于数字内容平台的管理具有一定 的参考意义。

ABSTRACT. 数字化时代，开放式创新平台为企业收集用户创意提供了新的渠道，领先用户能比一般用户更早的预见创新，因此领先用户识别是一种寻找有效创意的合理解决方案。本文以网络志为研究方法，通过对美创平台的深度观察，研究平台用户的特性，对领先用户进行了探索，并识别出了三种类似用户。本研究为企业识别领先用户，帮助企业快速识别有效创意提供了精准有效的方案。

ABSTRACT. 第四次工业革命带来了前所未有的城市治理变革，我国各超大城市都在全面探索数字化转型的这一技术治理导向的城市治理创新之路。与此同时，城市管理体制发展正在经历“重心下移”的趋势。在此双重逻辑下，行政层级上如何回应提升政府治理能力的需求？从技术-组织耦合视角，通过对上海市城市运行管理中心“一网统管”实践案例的深入分析，系统考察了数字政府平台的区－街统合中需要创新的四大清单，职责清单、任务清单、流程清单和人员清单，及其相应的耦合悬浮四大实践困境表征，即责任分担困境、上下整合困境、部门协同困境和事务处理困境。并据此提出相应的优化路径，以期有效解决在数字化转型背景下的城市治理困境。

ABSTRACT. 基于信息系统有效使用理论，本文采用混合研究方法结合多源数据，通过三个子研究设计揭示了消费者参与的形式、测度体系与影响效应。研究表明，移动医疗服务价值共创的消费者参与是技术赋能下消费者与各利益相关者资源交互与整合的过程，包括消费者-提供者参与、消费者-消费者参与、消费者-技术参与，这三个二阶维度构成了消费者参与的层次结构。同时，基于消费者参与形式构建了消费者参与的测度体系，并利用专家与用户评价、信效度检验与外部效应检验验证了测度体系的有效性与稳健性，表明本文所构建的测度体系可以为后续实证研究提供可操作化的测量量表，也为丰富健康情境下的价值共创研究以及信息系统有效使用理论作出了相应贡献。

ABSTRACT. 双寡头广告竞争是一个备受关注的市场现象。在现有文献中，Lanchester模型是最经典的双寡头广告竞争模型之一。当前，广告的效果受到广告弹性和口碑效应的影响越来越大。然而，在Lanchester模型的相关研究中，很少对这两个因素进行全面和深入的讨论。因此，本文提出了广义的Lanchester模型，综合地考虑广告弹性和口碑效应两个指标，并采用一般化的参数来描述相应的指标，而非固定的常数。基于该模型，本文构建了有限时间的双寡头广告博弈模型。接着，本文对该博弈模型的闭环均衡广告策略及其稳态进行了分析，推导出其理论性质并给出了数值解。在此基础上，本文进一步对广告弹性和口碑效应进行了参数敏感性分析。本文的模型可以更准确地描述广告竞争现象，从而为双寡头市场下的企业提供更有效的广告策略。

ABSTRACT. Video has become an emerging carrier of user-generated content (UGC). As a branch of self-media videos, product review videos posted by influencers have become an influential channel in shaping consumers’ purchase decisions. In the past, studies on influencer marketing have largely focused on textual and pictorial social media posts, while there was a lack of research on unstructured UGC videos, from which we can extract deep cognitive and affective information. In this paper, we constructed a theoretical model to explain the influence of product review videos on viewers' attitudes based on the cognitive-affective framework and authenticity theory. Specifically, we posit that viewers’ attitudes towards the product and the influencer will be influenced by both cognitive cues (i.e., information amount and topic diversity) and affective cues (i.e., vocal and facial emotional intensity) because these cues will affect perceived authenticity on influencers. In addition, such effects will differ across different types of videos (i.e., shopping-haul videos and anti-haul videos). A mixed-method approach was proposed to test the theoretical model. In Study 1, we collected product review videos from Bilibili.com, used text mining, sentiment analytics, audio analytics, and facial expression analytics tools to extract video features, and conducted regression analyses on viewers' attitudes (i.e., viewers' sentiment towards the product and the influencer). We further proposed a lab experiment to establish causality between video features and viewer attitudes, and to elucidate the mediating role of influencer authenticity. The contribution and implication of the research are discussed.

ABSTRACT. 在线医生团队的多样性信息可能起到“双刃剑”作用，不同地影响患者。本文从多样性视角研究医生性别、科室及医院多样性对团队及其领衔专家绩效的影响。从领先健康平台上收集的2 588个团队相关数据，并进行实证建模分析。研究表明：性别和科室多样性分别正向和负向影响团队绩效，高级职称医生人数占比负向调节性别多样性的影响，这些多样性均正向影响领衔专家个人绩效。研究结果对于医生团队组建和在线服务绩效管理有理论和实践意义。

ABSTRACT. With the growing popularity of voice assistant, they have revamped how people use technology and connect with brands conveniently. Empirical studies have revealed that factors motivating people to use voice AI assistant include many factors, but a common theme is their capabilities. We believe voice assistance's capabilities cannot be seen as a single construct, we focus specifically on the computational and cognition functional ability of voice AI assistant. According to the analysis of a real interaction data set from voice AI assistant——Xiao Ai classmate voice assistance—— company, we find that the capabilities of computational and cognition is positive to service quality, and higher service quality will make users feel more intelligence. with the expectancy violation, service success as a moderating variable to explain the relationship between computational capability and intelligence preference. This research contributes to the nascent literature on voice AI assistant in customer service and has managerial implications both for how AI assistance should be designed.

ABSTRACT. 求职市场信息不对称以及低效的现状对职位推荐方法提出了更高的要求。一般商品推荐中最大化用户点击的目标并不适应职位推荐情景下互惠和竞争的特征，同时求职平台本身数据稀疏的特征进一步限制了现有职位推荐方法的效率。进一步的，职位推荐方法的可解释性决定了使用者对其的信任和理解，进一步影响了职位推荐方法在实践中的应用范围。为了解决以上问题，本文提出了一个可解释的双边异构图竞争迭代模型。首先，本文设计双边异构图整合来自求职者和职位的多源信息，通过图结点的连接和信息传递可以有效应对求职情境下数据稀疏的问题。其次，迭代模型以HR 的点击为目标，充分考虑求职者和职位的双边偏好，推荐满足互惠特性的职位。再者，模型中加入了一种竞争增强的策略，显式化地建模求职者在职位上的竞争热度和求职者的竞争偏好，通过两阶段优化实现对竞争热度的分散。 最后，本文在图网络中设计了多种粒度的注意力机制用于挖掘求职者的个性化偏好并实现具备解释性的职位推荐。本文在真实招聘平台数据集中进行了大量的实验，验证了推荐模型的有效性，鲁棒性和可解释性。

ABSTRACT. This paper analyzes the user's comments on an mobile platform of medical and senior care (MPMSC) to understand the user's concerns and help the platform operators improve the platform functions and services. Based on LDA (Latent Di-richlet Allocation) model and content analysis method, this paper analyzed 2569 user reviews about MPMSCs in Apple App store, and a theme framework of user review on the MPMSC is developed. The framework includes four first-level topics such as overall recognition, service convenience, service quality, and system quality, as well as 11 second-level topics. The conclusion enriches the relevant theoretical research of mobile application evaluation, and provides man-agement enlightenment for the platform and government to promote the development of MPMSC.

ABSTRACT. Contents and information behaviors as the main vector of micro-blog can be analyzed to provide insights into what, why, and how contents influence information behaviors in crisis situation, which help crisis management understand group users’ behaviors and the characteristics of sociocultural systems. In our research, we examine whether the affective dimensions and non-emotion dimensions (using Cox proportion hazard model extract features) of micro-blog contents associated with diffusion behavior and non-diffusion behavior in terms of quantity in the social media context of earthquake event. Results show that emotion contents have more significant influence on diffusion behavior than non-diffusion behavior, while non-emotion contents have more significance effect on non-diffusion behavior than diffusion behavior. The results give implications for both practitioners and scholars who are interested in further studies on crisis management and information behaviors research in the social media context.

ABSTRACT. 本文主要基于新冠疫情数据和在线旅游评论数据，探究新冠疫情对游客旅游情感的影响效应。首先，基于现有理论建立新冠疫情与旅游情感的假设关系，再通过PAD（Pleasure-Arousal-Dominance）三维情感分析模型提取旅游评论中的游客PAD情感，接着建立实证计量模型，最后运用双重差分方法估计模型，并且进行一系列稳健性检验后，以此得出最终的实证结果。研究结果发现，新冠疫情已经给游客情感带来显著影响效应，同时检验了旅游景区类型和旅游景区等级的调节效应。

ABSTRACT. Medical crowdfunding has been developing in many countries and helping people cope with the challenges of medical issues. This study explores the donation intention of medical crowdfunding users on online platforms. Based on dual-system theory, empathy-helping hypothesis and trust building model, a model was constructed to explore the factors affecting the donation on medical crowdfunding. We used a survey to collect data from people who have donated to medical crowdfunding projects. The analysis results reveal the influence of negative emotion appeal and familiarity on empathy, and the influence of structural assurance and third party seal on perceived credibility. This study not only expands the theoretical research on users’ behaviors in the context of medical crowdfunding, but also provides enlightenment for optimizing the process of medical crowdfunding projects.

ABSTRACT. The liberalization of trade and globalization bring challenges as well as opportunities to companies, especially for the Small and Medium Enterprises (SMEs). In order to reduce time and costs, while increasing the quality of products, an efficient implementation of systems engineering process is necessary. However, even if a few systems engineering standards especially address SMEs, surveys show that SMEs hardly use formalized processes, resulting in poor process reproducibility and monitoring, among other drawbacks. Indeed, because of strong resource limitation, SMEs have difficulty to estimate any short-term benefit in spending time formalizing their processes. Against this background, this paper explores a methodology to support project managers in fostering the progressive deployment and standardization of engineering processes in SMEs starting from the perspective of their own experience and referring to the international systems engineering standards. Our proposal stands by the companies’ side to help companies to make their engineering processes evolve by progressively aligning them with the systems engineering standards without disrupting the entire organization and practices of the company.

ABSTRACT. Recently, short-video platforms have become popular among the middle-aged and elderly. While some studies proposed that excessive use of short-video platforms may lead to many psychological problems, little knowledge is about how to help the middle-aged and elderly use platforms reasonably and gain subjective well-being. Drawing on generativity theory and social cognitive theory, this study demonstrated that middle-aged and elderly users who have a higher level of need to be needed would achieve a higher level of subjective well-being and build more social interaction on short-video platforms. Especially, through building more social interaction on short-video platforms they can achieve a higher level of online subjective well-being. Moreover, when middle-aged and elderly users received more family cognitive support, the positive relationships of need to be needed with subjective well-being and social interaction on short-video platforms would be stronger, however, the positive relationship between social interaction and subjective well-being would be weaker.

ABSTRACT. AI technology empowers AI agents to recognize and convey emotion and social cues, creating frequent interaction between consumers and AI agents, and an emerging human-AI relationship emerges. To advance our understanding of this human-AI relationship, this study proposes that perceiving a mental state is positively associated with the human-AI relationship and investigates the underlying mechanisms. Specifically, a survey was conducted to test the hypotheses. The results show that two dimensions of empathy are positively associated with harmonious human-AI relationships through elevated perceived anthropomorphism and psychological empowerment. Furthermore, this study verified interaction effects, comparative effects, and service stages differences. Finally, theoretical contributions and practical implications are discussed.

ABSTRACT. In live-streaming e-commerce shows, the reputation of influencers plays a central role because it affects the brand-side price negotiation and the consumer-side long-run profitability simultaneously. Building on the career concern literature, this paper examines the effect of the influencer's reputation on price negotiation. Our analytical and numerical results suggest that the price obtained from the negotiation is affected by the reputation concern non-monotonically. An influencer with a greater reputation concern may get a smaller discount. Besides, the brand, the influencer, and consumers are better off simultaneously if the influencer has a moderate career concern.

ABSTRACT. A substantial body of platforms literature has primarily characterized two-sided platforms as markets with cross-side network effects (CNEs). Most literature investigates how to attract more suppliers to leverage CNEs but ignores that CNEs driven by different suppliers may be heterogenous. To fill this gap, we identify two distinct suppliers i.e., individual hosts and professional hosts with three key differences in a set of housing rental platforms and examine how CNEs are influenced by different suppliers. Our results suggest that the quantity of individual hosts (vs. professional hosts) has larger CNEs on the renter size. In turn, renter size has larger CNEs on the quantity of individual hosts (vs. professional hosts), while renter size has weaker CNEs on the quality of individual hosts (vs. professional hosts). These findings generate important implications regarding how two-sided platforms may better govern ecosystems with different participants.

ABSTRACT. 本文通过分析新冠肺炎爆发前后的在线评论数据集及患者向医生咨询的线上会诊记录，采用将词共现分析与LDA模型结合的CO-LDA模型进行评论主题挖掘，使用决策树算法及 libsvm 对各主题维度的子句进行情感分析和情感倾向值计算，探索疫情爆发前后患者就医行为的改变以及疫情的爆发如何对患者的情感倾向和就医体验产生影响。主要研究发现是：疫情爆发后，在线医疗平台每日在线咨询量显著增加，其中咨询量最多的科室为内科，来自湖北省的咨询量显著增加。疫情爆发后，患者对线上问诊就医体验满意度提高，对线下问诊就医满意度降低。研究结果能够帮助在线医疗平台及医院了解患者关注主题及情感倾向，针对性地对就医服务流程进行改进，改善疫情期间患者的就医体验。

ABSTRACT. 面向在线健康社区需要向用户推荐既感兴趣且能改善其健康状况的干预方案。为此，本文提出了融合效用与兴趣的在线用户健康干预推荐模型，先利用注意力机制对用户兴趣进行学习，同时计算待推荐方案对其参与者的预计疗效，接着评估干预方案对目标用户的效用，最终结合方案效用和用户兴趣得出推荐结果。实验结果表明与基线推荐模型相比，本文所提出的模型不仅具有更好的推荐精度，还能有效提高所推荐干预方案对于用户健康改善的效用。

ABSTRACT. In the field of public health, suicide risk prediction is an urgent problem to be solved. According to psychological characteristics, it is valuable to consider users’ historical post in addition to current post for predicting suicide risk. Based on this rationale, this paper proposes a deep learning-based suicide risk prediction framework (DLDHI) considering dynamic historical information. To capture the dynamic and complicated information of historical post, this paper designs an improved unit based on long short-term memory. The importance and effectiveness of the prediction framework and its components are verified by comparison with the benchmark model and ablation ex-periments.

ABSTRACT. 在线医疗服务是缓解众多医疗问题的重要方式，研究旨在探讨用户在使用在线医疗APP的过程中会有哪些影响信任形成的因素，以及这些因素会对信任产生什么影响。研究采用各类在线医疗平台APP的用户评论文本，以信任源理论为基础，结合模糊数学理论，通过情感分析，从服务平台、服务主体、服务本身三方面出发，构建用户信任模型，挖掘文本中包含的信息。其结果能更好地服务于用户、医生、平台管理者。

ABSTRACT. Constructing a proper SME credit risk assessment index system and developing a predictive model that delivers with excellent performance will reduce the uncertainty of financial institution loans and ensure better development of supply chain finance (SCF). This paper proposes an integrated SME credit risk assessment index system and an innovative prediction model called XGBoost-RF to forecast SMEs’ credit risk. The results indicate that (1) the final assessment system offers 31 specific indicators for 5 dimensions, namely, SME characteristics, core enterprises characteristics, item characteristics, the operational status of the supply chain, and the macro-environment. (2) The assessment system and the XGBoost-RF model proposed in this paper exhibit excellent predictive performance in SCF. (3) Debt-paying ability most affects SMEs’ credit risk. (4) The effects of some new influential factors (e.g., the level of information processing and top management team concurrent posts) on SMEs’ credit risks are also verified.

ABSTRACT. By the end of 2020, the number of credit cards issued in China had reached 778 million, and with the impact of the new crown pneumonia epidemic, the default rate of credit cards in China has been increasing year by year. For the banking industry, credit card business is an important part of its personal loan business, and it is crucial to forecast the default probability of cardholders. A robust predictive model is not only a useful tool for banks to make judg-ments at the time of credit card application, but will also help customers to realize that this is an action that may harm their credit score, thus achieving the effect of default prevention beforehand.With the continuous enrichment of cardholder information, traditional statistical tools can no longer meet the prediction needs, and machine learn-ing methods suitable for big data analysis have started to be applied in the field of credit card default prediction. Among them, the Gradient Boost Decision Tree (GBDT) algorithm has emerged with various improvements based on GBDT, including XGBoost, LightGBM and CatBoost, because it can achieve better results in different scenarios. Among them, CatBoost is the improved version of GBDT with better comprehensive effect. Based on CatBoost al-gorithm is widely used in e-commerce, disease prediction and other fields, this paper uses CatBoost algorithm to predict credit card default probability.In this paper, the cardholder information of American Express credit card during 2017 is selected as the dataset, the variables are made easy to read by changing the data format, exploratory analysis is performed on 190 variables, various visualizations are tried, the categorical variables among them are selected, and Catboost is used to train the classifier and make predictions, and good accuracy is achieved.

ABSTRACT. 近年来社区团购发展迅速，为满足社区团购平台评价的需要，本文提出一种复杂决策情境下社区团购平台选择模型。首先依据现有文献及平台特征，构建了一套社区团购平台的多指标评价体系。接着，本文提出加权拓展概率语言Power平均（WEPLPA）集成算子，并分析算子的优良性质。进一步，通过价值函数与权重函数的双重转化，本文提出PLTS环境下的WEPLPA-CPT-EDAS评价模型。最后，利用社区团购平台优选实际案例评估和多角度对比分析，验证了模型的有效性和优越性

ABSTRACT. Artificial intelligence system is more and more widely used in enterprises. The research on the application effect of artificial intelligence system is of great significance. Taking safe driving as a scenario, this paper investigates the influencing factors of effective use (improving drivers' safe driving behavior) of intelligent safe driving assistance system in enterprises. Based on the theory of person-environment fit, this paper proposes a research model on how individual factors (i.e., age) and organizational factors (i.e., safety assessment system and workload) affect the effectiveness of the system. Further, we analyzed and verified the research model with the driving behavior data from a large petrochemical enterprise for 4 years. The results show that the intelligent safe driving assistance system is more effective for older drivers. When the enterprise is equipped with the corresponding safety assessment system or the workload is low, the safe driving assistance system will be more effective. At the same time, there are also significant interactions among the above factors. When the workload is large, the safety assessment system plays a greater role. The positive effect of safety assessment system on the effectiveness of intelligent monitoring system is more obvious among older drivers. The negative effect of workload on the effectiveness of intelligent monitoring system is more obvious among young drivers.

ABSTRACT. 按需服务平台将供给和需求进行精准及时的匹配，而零工经济的发展改变了按需服务企业的用工模式。本研究基于双边市场理论，构建了垄断市场中，在雇员模式、混合模式和零工模式下的博弈模型，对零工经济下按需服务平台定价及用工模式选择进行研究，不仅明确了同边和跨边网络效应对平台的最优价格、需求规模、零工从业者数量和最大利润的影响，也发现了在不同情况下平台的最优用工模式，为按需服务平台的发展带来一些管理启示。

ABSTRACT. This paper constructs a research theoretical model based on the social identity theory to examine the effects of in-formation disclosure and emotional disclosure of posts on the number of replies received to a post in online health communities for people with depression. There are several findings in our research. First, information disclosure negatively impacts the number of replies. Second, when posts show higher levels of negative emotion, they receive higher replies, and the degree of suicidal tendencies positively impacts the number of replies, while positively mod-erating the effect of information disclosure on the number of replies.

ABSTRACT. 本文探讨了全球经济政策不确定性对加密货币收益稳定性的影响。本文的研究结果表明，在样本期内加密货币可以作为抵御经济政策不确定风险的避险资产，经济政策不确定性越高，加密货币的流动性波动和收益波动越低。此外，加密货币的流动性波动会显著的抑制经济政策不确定性对加密货币收益波动的负向影响，但是这种抑制作用在COVID-19大流行期间更为显著。本文还发现了一些基于国家层面经济不确定性以及基于加密货币特征的异质性结果。

ABSTRACT. 作为当前最具影响力的数字加密货币，比特币的巨大价格波动一直是国内外学者关注的焦点。本文基于行为金融学理论，研究在比特币交易中用户行为变化对比特币价格的影响。为刻画比特币的用户行为，本文进一步运用复杂网络的相关理论，通过比特币用户交易网络结构特征演化反映用户交易行为演化。比特币用户交易网络是将实际用户之间的比特币交易映射成异构网络，它不仅是用户交易的网络化体现，而且通过交易网络结构特征可以发现在现实中不易观察到的用户行为特征的演化。最后，通过分析网络结构指标对比特币价格的影响，进而发现用户交易行为对比特币价格的影响机制。利用2015年1月至2019年7月31日间的比特币真实交易数据的实证研究发现：用户活跃度、用户囤币行为、用户交易强度、用户紧密度和机构投资者交易频率的变化对比特币价格波动具有正向影响。尤其当比特币价格处于波动期时，这种正向的影响更加显著。本文的研究也发现用户行为特征变化对比特币价格波动影响存在延迟效应，这使得利用用户行为特征来预测比特币价格波动具有一定合理性。本文的研究对数字货币价格机制具有一定的管理启示。

ABSTRACT. Recent studies show that, when choosing between risky alternatives, people do not only integrate values and probabilities for each gamble but also use component comparison procedures to compare relative values and probabilities across gambles. This suggests that the salience of the gamble and emotional arousal may play an important role in risky decision-making. This study explores the effect of attention, pupil-linked arousal, and salience on the risky decision-making processes. We find that when the expected utility calculation is easy, people do the calculation, however, when the expected utility calculation becomes harder, they compare payoffs and are attracted to the salient option. Further, we find that pupil-linked arousal reflects the cognitive effort involved in the calculation of the expected utility and the cognitive effort employed to conquer the attractiveness of the more salient option.

ABSTRACT. 作为一类新兴的隐私计算方法，联邦学习技术联邦学习实现了“数据不动而算法动”，从而为解决“数据孤岛” 提供了新的技术解决途径。然而，每个企业加入数据联邦的决策与其收益分享方式直接相关，如果不能通过合理的收 益分享方法来为企业提供参与激励，联邦学习技术也无法成功地促使企业之间真正实现其算法目的。本文模拟了一个 企业的随机图网络并讨论了在不同收益分享机制设计下，企业之间如何形成数据联邦及其算法收益。本文的核心结论 是，三种联邦收益分享机制都有可能成为最优机制，这主要取决于联邦学习算法利用数据能力和联邦企业网络规模大 小的影响。

ABSTRACT. Many organizations have adopted enterprise social media to improve employees' job performance. It has become common for employees to use enterprise social media to deal with work during non-working time. However, the impact of non-working time enterprise social media use remains unclear. Based on conservation of resource theory, this paper constructs a research model to study the relationship between enterprise social media and job performance at different times. Using structural equation model to analyze 323 employee’s data, the results show that: (1) Neither working nor non- working time enterprise social media use has significant effect on emotional exhaustion. (2) Both working time and non-working time enterprise social media use have promoting effect on organizational commitment. (3) Emotional exhaustion has inhibited effect on job performance, and organizational commitment has promoting effect on job performance. Finally, the theoretical and practical implications of this study are explored.

ABSTRACT. Content creators, such as YouTube and TikTok influencers, attract growing attention from advertisers, which presents a novel tradeoff for the hosting platform. On one hand, allowing content creators to embed sponsored ads (CADS) in the content undermines the platform's own ad sales (PADS); On the other hand, the platform might benefit from CADS through commissions. We develop a game-theoretical model to examine this tradeoff, in which a group of content creators and their hosting platform compete with each other on ad sales. We find that the dual mode (i.e., allowing CADS) might be optimal for the platform, depending on the qualities of PADS and CADS. Unlike the literature where the relationship between the platform offerings and the third-party participation is exogenous, we show that the strategic relationship between PADS and CADS can be substitutable, complementary, or independent from each other, which is endogenously determined by the platform.

ABSTRACT. 现有研究强调CIO着承担数字化创新的主要职责，但鲜有探讨CIO如何克服资源困境进而推动组织的数字化创新。本文整合拼创和议题营销理论，采用组态理论的观点，认为在CIO个体特征和组织因素等条件下，CIO可以通过拼创或议题营销成功地实现数字化创新。借助模糊集定性比较分析法(fsQCA)对218对CIO/业务高管匹配样本的问卷数据进行实证分析，结果显示，在不同的条件下CIO通过拼创或议题营销使数字化创新达到较高水平。本文也讨论了关于CIO通过拼创或议题营销实现数字化创新的理论贡献和实践意义。

ABSTRACT. 保护环境、节能减排已成为世界共识。2020年，中国提出双碳政策，力争2030年前实现碳达峰、2060年实现碳中和。本文采取fsQCA的方法，基于我国30个省域2019年的数据，探究数字经济驱动下我国低碳发展路径，分人口、经济社会、资源三个层面考察了人口产业结构、数字经济发展水平、城镇化水平、碳减排政策规制和能源消费结构对地区碳排放强度的组合效应，得到影响地区碳排放强度的两种路径，分别为“数字经济-城镇化水平-低能源消费结构”路径和“数字经济-人口产业结构-碳减排政策”路径。

ABSTRACT. Multimodality is one of the important directions of AI-powered learning at present and in the future. Improving crystallized intelligence is one of the goals of AI-powered learning. In this study, we develop a theoretical model to explain the relationship between modality of AI and crystallized intelligence, based on the Biggs 3P model. We test the hypotheses using data from an experiment (N = 324) and found that modality of AI has a positive effect on deep learning approach and a negative effect on surface learning approach. The modality of AI can affect crystallized intelligence both directly and indirectly through deep learning approach. Moreover, we examine the moderating effect of technological readiness from learners’ perspectives. Optimism and insecurity have moderating effect on the relationship between modality of AI and two kinds of learning approaches respectively.

ABSTRACT. 已有研究表明，信息技术（IT）双元能力能够显著增强组织敏捷性和企业绩效。然而，当前尚未有研究探索如何培育企业IT双元能力。本文从首席信息官（CIO）和高层管理团队（TMT）知识交互角度，研究CIO与TMT知识交互机制（包括结构化和社会化交互）对IT双元能力的影响，并考虑环境动态性的调节效应。本文构建了结构性交流系统、社会性交流系统、环境动态性与企业IT双元能力之间关系的研究模型，利用结构方程模型对347家中国企业的调查问卷进行数据分析和模型拟合。研究结果表明，结构性交流系统和社会性交流系统都能正向影响企业IT双元能力，且两种交互机制在增强IT双元能力过程中存在替代效应；环境动态性正向调节社会性交流系统与IT双元能力的关系，而对结构性交流系统与IT双元能力的关系无调节效应。除此之外，三向交互结果表明，在动态环境下，结构性交流系统和社会性交流系统之间的替代效应会减弱。以上结论拓展了当前对IT双元能力培育的研究，并为企业如何构建IT双元能力提供实践指导。

ABSTRACT. 在线旅行社(OTA)越来越被认为是扩大消费者基础的重要渠道。然而，目前尚不明确OTA渠道的引入对航空公司收入有何影响。在本研究中，我们基于一个准实验，结合倾向得分匹配和双重差分方法，从航空公司提供的同质和异构服务角度实证验证了OTA平台的引入对其收益的影响。结果表明，OTA的引入导致自有平台的同质化服务收益显著下降，同时对异构化(辅助)服务收益产生积极影响。我们的研究结果对平台开发、多渠道战略和收益管理具有启示意义。

ABSTRACT. 本文首先讨论了体验型产品在线评论的不一致及其与商家信息呈现的不一致对消费者购买决策的影响作用，进而基于远程临场感理论，采用生动性、交互性、丰富性三个变量刻画AR技术特征，并探讨AR技术对消费者购买决策的影响作用。本文采用京东1000多个美妆产品的43万条评论验证研究模型，验证了在线评论的不一致性、在线评论与商家信息呈现的不一致性对消费者决策的消极影响，以及AR试妆技术对消费者决策的积极影响和调节效应。

ABSTRACT. 现有研究大多集中分析同边和跨边网络效应单个因素对平台发展的影响机制，却忽视其协同作用。本文利用 24149 条 Airbnb 的房源数据，构建网络效应与房东质量对房东响应行为的影响机制模型。实证结果发现，跨边网络效应和房东质量均正向影响房东响应行为；同边网络效应对房东响应行为具有负向作用；房东质量对网络效应影响房东响应行为具有差异性的调节作用。本文丰富了网络效应的相关研究，同时有助于平台管理者针对性地优化治理策略。

ABSTRACT. 在线下渠道提供服务的基础上，考虑医药零售商不提供线上医疗咨询服务、提供无偿及有偿线上医疗咨询服务三种服务策略，对比分析零售商和服务商最优价格与服务水平决策、线上线下需求变化及服务策略选择。研究发现：提供无偿线上服务仅在服务成本较小时会增加线上渠道需求和总需求；对线上服务收费并非总会减少线上需求；医药零售商的服务策略选择与开通线上服务的固定成本、消费者线上渠道偏好程度及消费者有偿服务偏好程度等有关。

ABSTRACT. The rapid growth of virtual reality (VR) technologies and computing power has given birth to immersive platforms, where users can immerse in a 3D virtual world and engage in various activities such as job training, remote collaboration, and innovative marketing practices. Through the lens of self-perception theory, this paper investigates how avatar design, i.e., user-avatar similarity, affects users’ self-concepts and shapes their behaviors in immersive VR. The preliminary experiment reveals that higher avatar-user similarity leads to higher task engagement in general. Furthermore, while a similar avatar promotes users to regulate their behaviors and achieve better performance in a procedural task, high similarity also inhibits users’ creativity by invoking habitual thinking, resulting in worse performance in generating original ideas in a creative task. This study is expected to contribute to HCI literature by revealing the value of avatar design and providing new perspectives in improving users’ experience in the immersive virtual world.

ABSTRACT. The textual risk disclosures in financial reports, which discuss the company’s potential risks from a forward-looking perspective, were rarely considered in financial distress prediction. Thus, this study explores whether the textual risk disclosure of financial reports can help predict the financial distress or not. To comprehensively extract information from the massive unstructured textual risk disclosures, the textual attributes are utilized to capture the linguistic styles of risk disclosures and an unsupervised topic model is adopted to identify the textual topics (the content of the text) in risk disclosures. Based on the textual risk disclosures of 4,039 financial reports for U.S. energy companies from 2006 to 2020, the empirical results demonstrate that the textual attributes and textual topics extracted from risk disclosures in financial reports can significantly improve the financial distress prediction performance compared with commonly used numerical variables (financial and market variables). Moreover, the textual topics in risk disclosures can provide more information than commonly used textual attributes for financial distress prediction. Last but most importantly, the textual risk disclosures become more and more useful relative to numerical variables as the predicting time horizon becomes longer. This study can help investors and regulators understand how to analyze the textual risk disclosures in financial reports and incorporate the textual information into financial distress prediction.

ABSTRACT. 本文使用大众点评（dianping.com）平台数据，通过双重差分模型揭示了用户生成内容平台中商户进入推荐榜单对商户的潜在影响。研究结果发现，进入推荐榜单给商户带来一定的积极影响：消费者更加愿意分享自己在该商户下的消费体验，该商户评论量显著提升；然而，由于用户初始期望与感知绩效之间的差异，商户的总评分显著下降；用户对于产品的取向更加单一，导致了人均消费额的下降。本文扩展了上榜效应的相关研究并通过分析上榜效应丰富了期望确认理论相关的文献。

ABSTRACT. O2O（Online to offline）平台将本地服务企业与消费者相连接，深刻地影响了本地服务企业的经营与绩效。在线消费者构成，本地企业的服务相关决策与平台相关决策将共同影响O2O平台上本地企业的绩效。基于平台生态系统视角，引入组态思维，运用模糊集定性比较分析（Fuzzy-set qualitative comparative analysis, fsQCA）方法探索影响O2O平台内本地服务企业绩效的因素组态。以影院为样本，采用比较静态的分析方法，考察在O2O平台的成长期与稳定期，绩效因素组态发生了什么改变。研究表明，高票价和高线上销售占比条件变量出现在影院所有高绩效组态中。在平台成长期，高排座率、低排片多样性和高自建平台具有替代性；而平台进入稳定期，排片和自建平台成为影院获取差异化竞争优势的关键。

ABSTRACT. 2022年3月，由新冠病毒奥密克戎变异株引发的疫情突袭上海。封控期间，上海接连发生生活资源不足、医疗资源稀缺、社区功能瘫痪等问题。传统求助热线无法正常运行，社交媒体就成为人们寻求帮助的重要渠道。本文以上海新冠疫情为例，以微博数据为研究对象，对新冠疫情爆发期间公众线上求助信息进行时空分析，探究其对危机治理的影响和作用，分析问题并提出针对性建议，为相关管理部门处理类似事件时提供科学的决策依据。

ABSTRACT. 数字政府建设以来，政务界面渐成公众获取公共服务主要渠道，但政务界面的公共服务供给特征如何影响公众的感知绩效尚未明晰。本文从界面治理理论视角切入，结合感性工学理论，采用交叉学科方法分析28个省级微信政务小程序界面。研究发现，服务形象、服务供给和服务创新是影响政务界面公共服务感知绩效三个维度；服务形象和服务供给分别受政务界面“外观形态要素”与“功能形态要素”两类供给特征影响，服务创新则是受界面整体影响；地域风景版面较小、证照卡包按需添加、专题服务列表导航且设置标题列举服务、小标题长度适中、整体字体适中、不设置其他信息区、设置底部导航区可以提升服务形象和服务供给维度的公共服务感知绩效。本文加深了学界对政务界面的理解，深化了界面治理理论内涵，并提出政府应当构建清爽、弹性、人文的政务界面。

ABSTRACT. 本文选取中国大陆31个省级行政区的数据构建关系矩阵，利用UCINET软件进行网络图谱、中心性、块模型、差异性和相关性分析，借助二次指派程序分析地域及疫情的调节作用。研究发现区域民间借贷风险网络存在风险中心，网络结构和位置特征均影响借贷风险传导。P2P平台表现出更明显的集聚效应，和实体借贷协同加剧民间借贷风险传导。东部省级行政区位于更核心的位置，疫情的调节作用不明显。相关部门应提前防范借贷风险，以进行公共危机管理。 We selected the data of 31 provincial-level administrative regions in mainland China to construct a relationship matrix, analyzed the network map, centrality, block model, difference and correlation by UCINET. Through the quadratic assignment procedure, we verified the moderating effects of regions and the COVID-19. Major findings include that there are risk centers in the regional private lending risk network and the network structure characteristics affect the transmission of lending risk; P2P (Peer-to-Peer) platforms show a more obvious agglomeration effect, and synergize with physical lending to exacerbate private lending risk transmission; the eastern provincial administrative regions are located in a more central position, and the moderating effect of the COVID-19 is not obvious. Relevant departments should prevent private lending risks in advance for public crisis management.

ABSTRACT. 正式借贷与非正式借贷渠道并存的二元结构是中国信用市场的主要特征。研究采用中国家庭追踪调查（CFPS）2014—2018年三期面板数据，选取Probit模型实证探究中国农村家庭的借贷渠道决策中是否存在同伴效应。研究发现：同伴效应对农村家庭借贷渠道选择有显著的正向影响，但通过外部渠道获取的信息会削弱这种影响。此外，针对家庭特征异质性，同伴效应的作用程度存在差异。在考虑遗漏变量、因果识别和渠道干扰问题后，研究结论保持稳健。

ABSTRACT. 面向客观了解、掌握创新实体的技术创新能力的客观需求，针对现有研究存在的采用的专利指标有待扩展、未对专利类型进行细分等不足，本文构建了一套基于专利数据的机构技术创新能力测度方法，并以北交所首批上市的16家专精特新“小巨人”企业为例进行了应用研究。本文构建的测度模型涉及机构的外在显性表现（技术创新活跃度）和内在隐性价值（技术创新价值度）两个角度，能够较为全面的反映创新机构的技术创新能力，拓展了现有研究中单纯依靠专利基本计量统计指标开展技术创新能力评估的方法；同时在机构的专利隐性价值方面，本研究针对不同的专利类型，有针对性的设计了专利价值评估指标体系，并通过专家研讨的方式确定数据规范化策略和指标权重，对于未来相关工作的开展提供了数据基础和思想指导。

ABSTRACT. 本文从霍夫兰说服模型中信息内容的角度通过文本分析的方法对直播带货中主播的各种表达风格进行分类，然后基于不同类别的表达风格探究其对消费者购买意愿和社会临场感的影响，并探讨了社会临场感的中介效应及情境因素和商品类型的调节作用。本文采用真实直播间下相关数据来计算消费者社会临场，数据更加真实全面可信度更高。本文得到的结果可以完善传播说服理论在电商直播背景下的应用，从而更好地为电商平台和商家主播提供了实践指导。

ABSTRACT. 本文采用问卷调查的方法，揭示了政府助农直播对消费者购买意愿的影响机制。结果发现：官员主播的感知亲民性和身份权威感、直播所售农产品的区域品牌特性、直播场景的互动性、生产场景性等能通过消费者的认同、内化机制显著影响购买意愿。因此，政府助农直播应通过借助官员身份、放下官员“架子”、提供高品质、具有区域特色的农产品并借助真实的生产场景进行直播、加强与消费者互动来增强消费者的认同和内化，进而提升消费者购买意愿。

ABSTRACT. With the continuous development of ecological city construction under the concept of "ecological civilization", the creation of ecologically livable cities has become more and more important. Since urban livability involves a wide range of social life, the establishment of urban livability index evaluation system can help analyze urban livability and residents' quality of life, and then optimize and control urban spatial structure to promote high-quality urban development. This study takes Wuhan City, Hubei Province, as an example, and establishes a comprehensive index evaluation system based on 12 indicators in three criteria levels: economic, social, and environmental, and calculates a comprehensive score of urban livability for each district in Wuhan City, and conducts a comprehensive evaluation of the 13 administrative districts under Wuhan City. Based on the final scores, we analyze the livability and friendliness of each district in Wuhan, analyze the spatial pattern of the results, discuss the strengths and weaknesses of the livability of each district in Wuhan, make scientific reference suggestions to promote the coordinated development of each district, guide the rational allocation of resources, and provide a reference for decision making to promote the livable communities in each district in Wuhan.

ABSTRACT. 当前地理标记照片广泛应用于个性化旅游路线推荐，但大多数研究尚未考虑这些照片的视觉内容。为此论文提出了一个考虑景点视觉信息的深度学习路线推荐模型，该模型利用卷积神经网络ResNet50提取视觉特征并构建用户视觉偏好，基于包含双向LSTM编码器和注意力机制LSTM解码器的改进Seq2Seq模型，采用beam search算法生成推荐路线。使用真实数据集对论文所提模型进行了验证，结果显示其表现优于其它基线方法，表明利用景点视觉信息可有效提高推荐性能。

ABSTRACT. 新兴技术为传统媒体的数智跃迁提供了强大支持，智能电视作为典型代表，是客厅经济的流量入口和强大载体。电视台等内容提供者一方面享受着客厅经济的红利，另一方面也面临着多重挑战，例如电视剧接档期间的观众流失。借助智能分析技术，本研究在智能电视中电视剧接档情境下，探究内容产品相似度与消费者留存之间的关系，并发现电视剧相似度与消费者留存存在倒U型关系，为客厅经济中电视台在内容产品的序列决策方面提供了借鉴。

ABSTRACT. 摘要：［目的/意义］非遗信息搜寻作为短视频生态重要的一环，挖掘其用户信息搜寻行为的影响要素及其作用机理，有助于增强非物质文化遗产活力，提升非物质文化遗产的现代化传播力度。［方法/过程］本研究以刺激-机体-反应理论和传播生态学理论为基础，通过调查收集数据，利用层次回归分析法检验变量间的主效应和中介效应关系；进而运用模糊集定性比较分析方法探索上述因素间的组合效应。［结果/结论］研究发现内容层中短视频权威人物和社会层中的临界质量是影响用户搜寻意愿的主要因素。其中，内容层的权威人物是短视频满意度产生的必要要素；短视频满意度在短视频内容呈现与用户信息搜寻意愿间起到完全中介作用，在短视频系统质量、短视频权威人物、临界质量、虚拟社交距离与用户信息搜寻意愿之间存在部分中介作用。本研究丰富了短视频情境下非遗信息搜寻行为的理论基础，同时对非遗信息的制作和传播提供了相应建议。

ABSTRACT. 内容平台通过短视频带货、直播带货等形式开启电商业务，通过佣金获得利润。在开展电商业务的过程中，内容平台会与电商平台合作构建联合渠道，也会自主构建自营渠道（如：抖音小店）以及同时运营两种渠道。本文构建主从博弈模型，分析内容平台在三种渠道模式间的决策以及决策对电商平台的影响。研究发现内容平台的决策与商家流量变现能力有关，且会对电商平台利润产生非连续的影响。

ABSTRACT. 从宏观经济、传统金融行业、互联网行业和互联网金融行业等维度构建混频数据集，用于测度和预测互联网金融风险水平。研究表明：随着互联网金融从“缺门槛、缺规则、缺监管”过渡到“高门槛、严规则、强监管”，行业风险水平整体呈下降趋势；银行不良贷款、网络借贷、互联网金融指数波动和互联网金融规模对风险变化有较高解释能力；中国互联网金融存在高低风险区制转换，未来会经历温和上升过程，但整体仍处于低风险区制。

ABSTRACT. 本文以启发式—系统式模型（HSM）为理论基础，基于某B2C平台客服聊天与交易的实际数据，会话分析视角下采用文本挖掘、情感分析等方法实现情感和交互变量的测量，通过logistic回归对消费者购买转化的影响因素进行分析。主要研究发现是：在启发式线索中，会话中的消息数量、表情符号对消费者购买转化存在正面影响，消息长度、客服响应时间对消费者购买转化存在负面影响；在系统式线索中，消极情感强度对消费者购买转化存在负面影响，积极情感强度对消费者购买转化没有显著影响。

ABSTRACT. 针对金融欺诈检测方法业务可解释性低，忽视欺诈个体间的关联信息特征提出融合多特征的改进Stacking金融欺诈检测模型。该模型结合有监督分层策略，从行为和关联这两个信息维度挖掘账户特征，在改进Stacking集成学习框架中实现异质特征融合，并在某互联网金融公司交易数据集上实验。证明改进Stacking集成学习框架显著提高了欺诈检测效果，避免在数据端直接融合导致的特征维度冗余问题。同时实验证明融合关联特征的欺诈检测模型在准确率、召回率等各项指标上都表现出更好预测性能。

ABSTRACT. 开发利用数据资源是数字中国建设的重要任务,开展基于用户评论内容的数据资源应用是信息资源管理学科的前沿交叉科学问题。本文针对基于在线评论情感分析的鲜果动态定价问题，首先建立融合边缘采样和协同训练的在线评论情感分析方法，然后构建基于在线评论情感分析的鲜果动态定价模型，最后通过融合高斯回代的交替方向乘子法求解模型。研究结果表明，本文提出的算法在收敛性上有优越性，为鲜果动态定价问题提供了新策略。

ABSTRACT. 本文采用行为实验的方法，以认知信任理论为基础，探索图片评论的数字化加工程度对消费者购买意愿是否会产生影响，以及该影响如何发生。我们的研究发现：图片评论的数字化加工程度对消费者购买意愿的影响呈倒U型，消费者的认知信任随着数字化加工程度的增加而降低，且认知信任在数字化加工程度影响消费者购买意愿的过程中起中介作用。

ABSTRACT. 本文采用多层线性模型，通过对Indiegogo数据的研究，探索了在“连续发起人层-项目层”的层次特征下众筹绩效的影响因素。主要研究发现是：项目质量信号（视频数、图片数）、项目交互行为（更新数、评论数）正向影响着众筹绩效；连续发起人经验（发起项目数、支持项目数）对众筹绩效存在着正向的跨层作用；连续发起人社会资本（总评论数）积极地跨层调节着图片数、项目评论数和绩效之间的关系，但在调节更新数和绩效之间的关系时是消极的。

ABSTRACT. 本文基于FISHBEIN合理行为理论建立研究模型，探讨了新冠疫情防控常态化背景下公众产生倦怠情绪的主要原因，以及公众倦态情绪对疫情防控行为的影响作用，并进行实证检验。研究结论表明：信息疫情对公众倦怠情绪有正向影响，规范性社会影响和信息性社会影响对倦怠情绪有负向影响；信息疫情负向影响防控行为，且全部通过倦怠情绪产生；规范性社会影响和信息性社会影响正向影响防控行为，且部分通过倦怠情绪产生；倦怠情绪对防控行为有负向影响。

ABSTRACT. Understanding how government short videos promote citizens’ policy compliance in times of epidemic outbreaks is worthy of attention. Based on grounded theory, this study constructs a theoretical model of government short videos influencing policy compliance taking China's interview data as evidence. Results show that government short videos have significant effects on citizens’ policy compliance through four cognitive appraisals: epidemic, policy, government-public relationship, and social influence. In addition, resilience as an individual feature moderate the relationship between these cognitive appraisals and compliance. Findings contribute to the study of COVID-19 policy compliance and enrich the literature on policy compliance antecedents from the perspective of information sources and cognitive appraisals. In addition, this study provides targeted theoretical guidance and increases the understanding of how government short videos may be used to promote policy compliance during pandemics in and beyond COVID-19.

ABSTRACT. 区块链食品追溯系统可以改善食品供应链中信息不对称的问题进而促进食品安全状况的提升，对消费者系统使用意愿及其影响因素的研究有助于促进系统的推广应用。本文在UTAUT模型的基础上结合区块链食品追溯系统的特点构建了系统使用意愿模型，运用结构方程模型进行了实证分析。研究结果表明：感知透明度、社会影响和便利条件均正向显著影响使用意愿；感知透明度对男性消费者使用意愿的影响更大，而便利条件对女性消费者使用意愿的影响更大；不安全食品购买经历和食品安全意识都显著正向调节感知透明度与使用意愿的关系。

ABSTRACT. 短视频快速兴起与发展的背景下，从顾客体验视角理解短视频场景营销对消费者购买意愿的影响因素与作用路径，是提升短视频质量，促进消费者购买意愿，发挥短视频场景营销价值最大化的重要前提。以S-O-R模型为基础，引入时效性加入自变量，构建短视频场景营销消费者购买意愿模型。依据问卷调查方法获取的475份数据，采用结构方程来验证假设及变量的净效应，采用模糊集定性比较方法（fsQCA）来探索整体视角下形成高消费者购买意愿的条件组态。

ABSTRACT. 自2019年生态环境部和发改委联合印发《长江保护修复攻坚战行动计划》以来，长江流域省份已经广泛开展了城市管道修复PPP项目试点工作，以实现污水处理的提质增效。本文从安徽省芜湖市城市管网修复项目管理实践出发，针对现有项目管理模式中存在的修复方案的设计进度与管网修复的施工进度不匹配导致工期长和重复作业的问题，提出基于改进支持向量机的城市排水管网修复方案选择模型，通过收集项目数据，分析验证了模型的有效性和可行性。

ABSTRACT. 随着直播电商蓬勃发展，AI虚拟主播逐渐进入直播间，目前较少研究关注虚拟主播与用户信任关系的建立。本文基于准社会互动理论，探究AI虚拟主播与用户互动中的人际吸引（社会、任务、外观吸引），以及主播的人格化程度如何影响准社会互动的建立，同时纳入情绪满足与认知促进，构建准社会互动视角下虚拟主播与用户信任建立模型。从电商直播情景丰富人与数字人交互信任理论，为直播商家提升用户信任度提供理论参考。

ABSTRACT. 为了应对医疗小样本问题，精准辅助医护人员开展传染性分类、风险预测管理。本研究基于计算设计科学范式设计、实现和评价一个基于小样本数据增强的重症肺炎患者传染性分类、风险因素识别与预测系统，以帮助医护人员管理重症肺炎患者。该系统包括四个组件：基于小样本学习的数据增强、基于可解释性的 LGBM 传染性区分模型、基于 Cox 回归的风险因素识别与评估模型。通过小样本学习获得更多高质量的研究案例，在此基础上利用传染性区分模型、风险因素识别与评估模型为医生提供预诊与风险预后等智慧服务。本研究不仅对开展小样本数据增强以及分类研究具有重要的理论意义，而且对于目前的新冠防治工作具有现实意义。

ABSTRACT. 如何优化在线有奖推介活动设计以获取更多新用户是商家和学者关注的重要话题。实践中，许多推介活动中出现了积分等媒介型奖励，然而这种新兴设计对用户感知与决策的影响仍知之甚少。基于动机理论和媒介相关研究提出，媒介型奖励会改变用户的社交动机和外在动机，对推介意愿的影响与其和推介对象的社交关系强度密切相关。三个实验的结果表明，当向弱关系发起推介时，媒介型奖励则会降低用户的感知社会风险，进而提升其参与意愿；当向强关系发起推介时，媒介型奖励会降低用户的感知推介价值，进而降低其参与意愿。研究结论有助于拓展对有奖推介活动、媒介研究和动机理论等多方面的认识，对于商家优化在线有奖推介活动设计具有指导意义。

ABSTRACT. 本文结合TOE框架，采用模糊集定性比较分析方法，从组态视角揭示提升企业数字化转型的关键路径。主要研究发现是：单一因素无法构成高水平数字化转型的必要条件，高水平企业数字化转型是多重技术、组织、环境因素共同作用的结果；具体地，四条不同的组态路径能实现高水平数字化转型，它们均是技术、组织、环境三方面因素的不同组合，而且，信息技术基础设施和CEO教育是关键的核心要素和辅助要素，行业竞争和研发投入之间存在匹配效应。

ABSTRACT. 中药材新闻推荐是典型的垂直领域新闻推荐问题，为了有效运用领域知识，本文提出一种基于知识图谱的中药材新闻推荐方法。首先，从中药典籍中抽取实体和关系，构建中药材知识图谱；其次，通过基于注意力机制的知识感知卷积神经网络得到新闻嵌入表示；然后，基于用户历史点击新闻及侧面信息，运用基于注意力机制的深度神经网络，生成Top-K推荐列表；最后，通过真实数据集实验，验证了本文模型效果优于基线模型，且具有一定的可解释性。

ABSTRACT. The referral reward program (RRP) is a social marketing method by which firms reward existing users and encourage them to recommend products or services to their friends. Prior research has primarily focused on the impact of RRP design on users’ participation, however, the role of individuals’ characteristics is unexplored. Based on regulatory focus theory and self-efficacy theory, this research proposes and investigates the effect of users’ regulatory focus (promotion-focused vs. prevention-focused) on their referral intention and explores its mechanism and boundary condition. The results of three experiments show that compared to the prevention-focused user, the promotion-focused user has higher self-efficacy to complete the referral task; and thus, has higher referral intention. This effect will be attenuated when the tie strength between inviter and invitee is strong. The findings not only contribute to the research on RRP and regulatory focus but also can provide guidance for firms to optimize their RRPs.

ABSTRACT. 针对区域间优质医疗资源分布不均，区域医疗服务质量可能存在较大差异的特点，进行不同地区医疗服务质量影响因素差异分析具有重要的意义。为了探究我国不同经济水平地区医疗服务质量影响因素存在的差异，以经济水平较为悬殊的北京地区和西部地区的三甲医院为研究对象，基于患者的在线医疗评论，利用改进的BTM主题模型进行评论挖掘，基于主题挖掘结果和SERVQUAL模型进行三甲医院医疗服务质量影响因素识别。利用调查问卷和因子分析法修正并建立医疗服务质量影响因素指标体系，利用相似度算法计算两地区患者对各因素的关注度，从区域层次出发，利用卡方检验等统计分析方法，详细对比北京地区和西部地区三甲医院患者对医疗服务质量影响因素的关注度、好评率和服务满意度，并针对北京地区和西部地区医疗服务质量影响因素的差异提出相关建议，为政府部门合理调配医疗资源、出台相关政策、医疗机构提升医疗服务质量提供支持和帮助。

ABSTRACT. 疫情催化下，企业社交媒体技术广泛应用（ESM）为员工沟通和知识共享提供了新场景。基于心理契约理论并利用我国358名钉钉用户数据进行实证分析，我们发现，社区帮助动机与员工显性和隐性知识共享行为均积极相关，但组织帮助动机仅与隐性知识共享行为负相关；组织依恋和社区归属感与两种知识共享行为均显著正相关。进一步的中介分析表明，社区归属感能够增强社区帮助动机进而间接促进显性和隐性知识共享。通过纳入“个人-集体”心理关系视角，本研究突破了知识共享的个人“成本-收益”分析框架，能为企业制定ESM知识管理策略提供新思路。