Workshop

Our aims for this research forum and shared task workshop are to: 

• Bring together experts from related domains to better understand and explore how the knowledge contained within the social media realm can be best utilized for health-related tasks, 
• Release annotated data to the biomedical informatics research community for the development of data-centric systems, 
• Enable the direct comparison of systems on this domain of health data, and 
• Provide a platform for researchers actively working on social media health-related data and those interested to work in this domain in the future to collaborate and discuss ideas. 

This workshop and shared task follows the successful implementation of Social Media Mining for Public Health Monitoring and Surveillance Session (https://psb.stanford.edu/previous/psb16/callfor/papers/cfp-smm/) and the 1st Social Media Mining Shared Task Workshop at the Pacific Symposium in  Biocomputing in 2016.  There are two distinct components to the session, an interactive workshop and a shared task, which will run back-to-back in a day-long schedule just prior to the start of the conference,

For this component, we invite long and short paper submissions. Please see submission guidelines below. 

*Update: We also invite abstract submissions for discussion at the workshop.

Topics of interest include, but are not limited to:

• Methods for the automatic detection and extraction of health-related concept mentions in social media
• Mapping of health-related mentions in social media to standardized vocabularies
• Social-media-based interventions for health monitoring and surveillance
• Deriving prescription drug use and off-label use trends from social media
• Visualization of social media health data
• Information retrieval methods for obtaining relevant social media data
• Social media in precision medicine
• Infectious disease monitoring using social media
• Mining health-related discussions in social media
• Drug abuse and alcoholism incidence monitoring and interventions through social media
• Prediction/detection of abusive behavior using social media postings
• Disease incidence studies using social media
• Sentinel event detection using social media
• Search, collection, and analysis techniques for public health informatics using social media
• NLP methods for health-related consumer-generated (colloquial) text
• Classifying health-related messages in social media
• Automatic analysis of social media messages for disease surveillance and patient education
• Methods for validation of social-media derived hypothesis and datasets.

This year's shared task will have 3 subtasks focusing on social media text classification and concept normalization.

Further details about the shared task can be found at the Shared Task Website https://healthlanguageprocessing.org/sharedtask2/

Best performing teams will be invited to submit system description papers at the workshop.

Important dates*

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference. All papers focusing on natural language processing of social media texts for health-related tasks are welcome. 

• Full papers must have a maximum length of 10 pages including references.
• Short Papers may have a maximum length of 5 pages including references.
• Abstracts may have a maximum length of 1 page including 2 references. 
• System Descriptions (shared task participants only) may have a maximum of 4 pages including references. Accepted system descriptions will also be included in the workshop proceedings.

Please follow the standard submission guidelines of the AMIA annual symposium available here: https://www.amia.org/amia2017/call-participation

All submissions must be through Easychair. Submission link: https://easychair.org/conferences/?conf=smmhawst17

Committees

Program/Organizing Committee

• Graciela Gonzalez, University of Pennsylvania (gragon@upenn.edu)
• Abeed Sarker, University of Pennsylvania (abeed@upenn.edu)
• Nigel Collier, University of Cambridge
• Azadeh Nikfarjam, Stanford University
• Cecile Paris, CSIRO, Australia
• Michael J Paul, University of Colorado-Boulder
• Pierre Zweigenbaum, CNRS, France

Contact

All questions about submissions should be emailed to Abeed Sarker (abeed AT upenn DOT edu)