ABSTRACT. Educational systems are increasingly powered by complex AI models. Recommendation engines are guiding learners, information retrieval systems are supporting curricula construction, and automated assessment is influencing institutional evaluations. At the core of these systems lies the concept of knowledge representation, the formal structures that define how educational content, competencies, and learners themselves are modeled.

This invited talk will explore how knowledge graphs serve as foundational architectures for such systems, enabling both semantic richness and user-centered automation. We will dive into technical strategies for building knowledge graphs, and how they could be developed to support complex models, such as LLMs, or the broader systems built around them, to improve transparency, user agency, and explainability. We will show how structured representations, such as curriculum-aligned graphs of concepts, skills, and outcomes, can be combined with neural models to support adaptive and explainable decision-making. This neuro-symbolic approach brings together the strengths of data-driven learning and symbolic reasoning, making AI systems more interpretable and complementary to human intelligence rather than mere black-box predictors. In turn, this supports stakeholders’ understanding of algorithms’ predictions and ability to make informed decisions based on it.

ABSTRACT. This paper presents the development and implementation of a machine learning-based web service designed to predict residential rental prices in the Ukrainian real estate market. The study employs a comparative analysis of three regression algorithms - Multiple Linear Regression, Decision Tree, and Random Forest - to identify the most effective approach for rental price prediction based on apartment characteristics, including area, number of rooms, floor, building height, proximity to metro stations, pet allowance, and distance to city center. Using data collected from DOM.RIA during November-December 2024, the research demonstrates that the Linear Regression model outperforms more complex algorithms, achieving a Mean Absolute Percentage Error of 4.96% compared to 7.20% for Decision Tree and 5.51% for Random Forest. Feature importance analysis reveals that apartment area, number of rooms, and district location are the most statistically significant predictors of rental prices. The implemented web service architecture provides users with rental price forecasts and confidence intervals, enabling tenants and landlords to make informed decisions in an information-asymmetric market. This research increases transparency and efficiency in real estate transactions by applying accessible machine-learning techniques.

ABSTRACT. In this work-in-progress paper, we present Extractomat – our three-lingual Automated Term Extraction (ATE) framework for English, German, and Ukrainian. The framework follows a hybrid iterative approach for ATE in multilingual and cross-domain settings. The approach is tailored to extracting terms from scientific texts in scholarly domains. We report the results of our initial evaluation experiments with Extractomat over our OTRT dataset and an out-of-the-shelf Named Entity Recognition (NER) model over the English subset of the ACTER dataset. The results of these experiments are compara-ble to the best-performing solutions for multilingual ATE and NER. These findings indicate that the iterative combination of linguistic, statistical, and neural ATE methods, when fully integrated in Extractomat, has the potential to improve the State of the Art (SotA) in the mentioned settings.

ABSTRACT. The changeability of the modern world, individual needs and priorities, and societal requirements for higher education graduates are forcing universities to look for the best digital models to go beyond a one-size-fits-all approach to training and provide students with a tailored learning experience. The purpose of the research was to develop and approve innovative digital solutions to ensure a transparent, user-friendly and institutionally efficient system for building personalised learning paths. The research is conducted using the data obtained in the process of testing the developed module of the KSU24 e-platform of Kherson State University (tested with 378 first-year master's students). The study focuses on the following components of designing a student's tailored learning experience in the university environment: 1) institutional frameworks and regulatory measures to ensure the dynamic design of tailored learning experience in universities within the changing student mindset and technological progress; 2) digital tools and algorithms, including artificial intelligence and adaptive systems, for personalised learning paths to be automated and adjusted; 3) management initiatives facilitating the integration of decentralised decision-making mechanisms and end-to-end analytics, providing an open and transparent system for selecting elements of the student curriculum; 4) empowering students and improving their engagement by providing them an autonomy in choosing learning goals, academic resources and services; 5) principles of internal peer learning, including methods of horizontal knowledge sharing, teachers' adaptation to digital technologies and integration of mentoring practices to support the quality implementation of personalised learning paths. The main focus is on the implementation of innovative solutions through the KSU24 platform, including academic performance prediction models, visualisation tools for learning paths, and API integration with educational platforms. This contributes to the creation of a flexible and personalised student curriculum, an analytical framework for making effective decisions and ensuring their systematic monitoring. The study offers a set of innovative institutional and digital solutions that can be scaled to the unique needs of other higher education institutions for supporting student autonomy in designing their learning paths in the extreme conditions of martial law and limited financial resources of the universities.

ABSTRACT. This study presents the development and evaluation of a gamified simulation platform designed to enhance laboratory-based learning in higher education. Integrating artificial intelligence (AI), virtual and augmented reality (VR/AR), and smart system components, the platform was piloted across disciplines including biochemistry, materials science, and computer engineering. A mixed-methods approach—combining surveys, platform prototyping, and usability testing—demonstrated that gamified simulations significantly improve student engagement, conceptual understanding, and task completion rates compared to traditional lab formats. Key features include immersive visualizations, adaptive feedback loops, and interactive scenarios aligned with course-specific objectives. Survey data from 187 students revealed strong support for competitive and narrative-based lab tasks. At the same time, pilot results confirmed increased motivation and effective learning under both normal and disrupted conditions, such as remote learning during crises. The platform encourages creativity, experimentation, and autonomy by enabling safe digital environments for hands-on exploration. This work underscores the potential of AI-enhanced, gamified simulation tools to support scalable, resilient, and student-centered education. It offers a model for integrating cutting-edge technologies into university curricula.