Predicting Mental Health Status on Social Media

A Preliminary Study on Microblog
  • Bibo Hao
  • Lin Li
  • Ang Li
  • Tingshao Zhu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8024)


The rapid development of social media brings about vast user generated content. Computational cyber-psychology, an interdisciplinary subject area, employs machine learning approaches to explore underlying psychological patterns. Our research aims at identifying users’ mental health status through their social media behavior. We collected both users’ social media data and mental health data from the most popular Chinses microblog service provider, Sina Weibo. By extracting linguistic and behavior features, and applying machine learning algorithms, we made preliminary exploration to identify users’ mental health status automaticly, which previously is mainly measured by well-designed psychological questionnaire. Our classification model achieves the accuracy of 72%, and the continous predicting model achieved correlation of 0.3 with questionnaire based score.


microblog mental health prediction automation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Meltzer, H., Rebecca, G., Robert, G., Tamsin, F.: Mental health of children and adolescents in Great Britain. International Review of Psychiatry 15(1-2), 185–187 (2003)CrossRefGoogle Scholar
  2. 2.
    Xinhua News: Sina Weibo’s registered user reached 300 millions (2012),
  3. 3.
    François, M., Marilyn, W., Matthias, M., Roger, M.: Using Linguistic Cues for the Automatic Recognition of Personality in Conversation and Text. Journal of Artificial Intelligence Research 30, 457–500 (2007)Google Scholar
  4. 4.
    Jennifer, G., Cristina, R., Karen, T.: Predicting Personality with Social Media. In: Proceedings of the 2011 Annual Conference Extended Abstracts on Human Factors in Computing Systems, ACM (2011)Google Scholar
  5. 5.
    Yoram, B., Michal, K., Thore, G., Pushmeet, K., David, S.: Personality and Patterns of Facebook Usage. WebSci 2012 (2012)Google Scholar
  6. 6.
    Daniele, Q., Michal, K., David, S., Jon, C.: Predicting Personality with Twitter. In: 2011 IEEE International Conference on Privacy, Security, Risk and Trust and IEEE International Conference on Social Computing (2011)Google Scholar
  7. 7.
    Fan, Z., Tingshao, Z., Ang, L., Yilin, L., Xingguo, X.: A survey of web behavior and mental health. In: 6th International Conference on Pervasive Computing and Applications (ICPCA 2011), pp. 189–195. IEEE (2011)Google Scholar
  8. 8.
    Dong, N., Yue, N., Tingshao, Z.: Predicting Mental Health Status in the Context of Web Browsing. Web Intelligence 2012 (2012)Google Scholar
  9. 9.
    Michael, C., Xuan, W., Yinqi, H., Rui, X., Tian, J.: Microblogging, Online Expression, and Political Efficacy Among Young Chinese Citizens: The Moderating Role of Information and Entertainment Needs in the Use of Weibo. Cyberpsychology, Behavior, and Social Networking 15(7), 345–349 (2012)CrossRefGoogle Scholar
  10. 10.
    Derogatis, L.R., Savitz, K.L.: The SCL-90-R and the Brief Symptom Inventory (BSI) in Primary Care. In: Lawrence Erlbaum Associates (2000)Google Scholar
  11. 11.
    Huaping, Z.: ICTCLAS, Chinese Lexical Analysis System (2013),
  12. 12.
    Pennebaker, J.W., Cindy, K.C., Molly, I., Amy, G., Roger, J.B.: The Development and Psychometric Properties of LIWC 2007 (2007)Google Scholar
  13. 13.
    Chin-Lan, H., Cindy, K.C., Natalie, H., Yi-Cheng, L., Yi-Tai, S., Ben, C.P.L., Wei-Chuan, C., Michael, H.B., Pennebaker, J.W.: The Development of the Chinese Linguistic Inquiry and Word Count Dictionary. Chinese Journal of Psychology 54(2), 185–201 (2012)Google Scholar
  14. 14.
    Linhong, X., Hongfei, L., Yu, P., Hui, R., Jianmei, C.: Constructing the Affective Lexicon Ontology. Journal of the China Society for Scientific and Technical Information 27(2) (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Bibo Hao
    • 1
  • Lin Li
    • 1
  • Ang Li
    • 1
  • Tingshao Zhu
    • 1
  1. 1.Institute of PsychologyUniversity of Chinese Academy of Sciences, CASChina

Personalised recommendations