Finding People with Emotional Distress in Online Social Media: A Design Combining Machine Learning and Rule-based Classification
Name:
finding_people_with_emotional_ ...
Embargo:
2025-06-01
Size:
1.433Mb
Format:
PDF
Description:
Final Published Version
Affiliation
Univ Arizona, Dept Management Informat SystIssue Date
2020
Metadata
Show full item recordPublisher
SOC INFORM MANAGE-MIS RES CENTCitation
Michael Chau, Li, T. M. H., Wong, P. W. C., Xu, J. J., Yip, P. S. F., & Hsinchun Chen. (2020). Finding People with Emotional Distress in Online Social Media: A Design Combining Machine Learning and Rule-Based Classification. MIS Quarterly, 44(2), 933–956.Journal
MIS QUARTERLYRights
Copyright © 2019 by the Management Information Systems Research Center (MISRC) of the University of Minnesota.Collection Information
This item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.Abstract
Many people face problems of emotional distress. Early detection of high-risk individuals is the key to prevent suicidal behavior. There is increasing evidence that the Internet and social media provide clues of people's emotional distress. In particular, some people leave messages showing emotional distress or even suicide notes on the Internet. Identifying emotionally distressed people and examining their posts on the Internet are important steps for health and social work professionals to provide assistance, but the process is very timeconsuming and ineffective if conducted manually using standard search engines. Following the design science approach, we present the design of a system called KAREN, which identifies individuals who blog about their emotional distress in the Chinese language, using a combination of machine learning classification and rulebased classification with rules obtained from experts. A controlled experiment and a user study were conducted to evaluate system performance in searching and analyzing blogs written by people who might be emotionally distressed. The results show that the proposed system achieved better classification performance than the benchmark methods and that professionals perceived the system to be more useful and effective for identifying bloggers with emotional distress than benchmark approaches.Note
60 month embargo; published 01 June 2020ISSN
0276-7783Version
Final published versionae974a485f413a2113503eed53cd6c53
10.25300/MISQ/2020/14110