報告題目：KETCH: A Knowledge-Enhanced Transformer-based Approach to Suicidal Ideation Detection from Social Media Content
時間：2024年7月9日 10:00-11:30
地點：中關村校區主樓345
報告人：張東松教授
報告人簡介：
Dr. Dongsong Zhang is a Belk Endowed Chair Professor in Business Analytics (with tenure) in the Department of Business Information Systems and Operations Management at the Belk College of Business, the University of North Carolina at Charlotte (UNC Charlotte). He also serves as the interim executive director of the School of Data Science and holds an affiliate professor position in the Department of Computer Science at UNC Charlotte. His current research interests include mobile HCI, social media analytics, health IT, business intelligence, and online communities. He has published over 180 research articles in journals and conference proceedings, including journals such as MIS Quarterly, Information Systems Research, Journal of Management Information Systems, ACM Transactions on Accessible Computing, ACM Transactions on Management Information Systems, Communications of the ACM, Decision Support Systems, IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Transactions on Software Engineering, IEEE Transactions on Multimedia, IEEE Transactions on Systems, Man, and Cybernetics, IEEE Transactions on Human-Machine Systems, IEEE Transactions on Professional Communication, IEEE Intelligent Systems, and Information & Management, among others. He has received a dozen external research grants and awards from U.S. National Science Foundation (NSF), National Institute of Health (NIH), U.S. Department of Education, Centers for Disease Control and Prevention (CDC), and Google Inc., etc. According to Google Scholar, his work has been cited more than 15,000 times. He received his Ph.D. in Management Information Systems from the Eller School of Management at the University of Arizona in 2002.
報告內容簡介：
Suicidal ideation (SI), as a psychiatric emergency, requires immediate assistance and intervention. Most people with SI do not actively seek help from mental health professionals, which may result in irreversible consequences. Research has shown that individuals experiencing SI increasingly express their thoughts and emotions on social media platforms, making the latter a viable venue for suicidal ideation detection (SID). This paper proposes, develops, and evaluates a knowledge-enhanced transformer-based approach (KETCH) to SID from social media content. KETCH comprises several key design artifacts, including a social media-oriented SI lexicon, a model-level method for integrating domain knowledge (i.e., lexicon) into a state-of-the-art transformer, and aligned dynamic embedding and lexicon-based enhancement that integrate domain relevance and contextual importance of terms to effective SID. We evaluate KETCH’s performance with social media data in two different languages collected from distinct platforms. The results demonstrate the superior effectiveness, robustness, and generalizability of KETCH via a series of empirical evaluation and a field study. This research makes can have far-reaching impacts on public health, the economy, and society.
（承辦：管理工程系、科研與學術交流中心）
