欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2014, Vol. 31 ›› Issue (6): 814-820.DOI: 10.7523/j.issn.2095-6134.2014.06.013

• 计算机科学 • 上一篇    下一篇

微博用户的抑郁和焦虑预测

白朔天1, 郝碧波1, 李昂1, 聂栋1, 朱廷劭2   

  1. 1 中国科学院大学计算机与控制学院, 北京 100049;
    2 中国科学院心理研究所, 北京 100101
  • 收稿日期:2013-11-06 修回日期:2014-02-24 发布日期:2014-11-15
  • 通讯作者: 朱廷劭
  • 基金资助:

    Supported by NSFC(61070115),Strategic Priority Research Program(XDA06030800) and 100-Talent Project(Y2CX093006) from CAS

Depression and anxiety prediction on microblogs

BAI Shuotian1, HAO Bibo1, LI Ang1, NIE Dong1, ZHU Tingshao2   

  1. 1. School of Computer and Control Engineer, University of Chinese Academy of Sciences, Beijing 100049, China;
    2. Institute of Psychology, Chinese Academy of Sciences, Beijing 100101, China
  • Received:2013-11-06 Revised:2014-02-24 Published:2014-11-15
  • Supported by:

    Supported by NSFC(61070115),Strategic Priority Research Program(XDA06030800) and 100-Talent Project(Y2CX093006) from CAS

摘要:

临床心理学指出,心理健康状况通过人的行为表现,其中包括网络行为.传统的心理健康测评以自陈量表的形式为主.这不但要耗费大量的人工处理工作,更不能做到实时进行心理健康状态的获取.针对传统方法的不足,本文旨在通过新浪微博的环境,预测用户的心理健康状况,特别是抑郁和焦虑问题.通过批量获取微博用户的网上数据,验证了传统理论中人格和心理健康之间的相关性,并采用多任务回归学习预测微博用户的心理健康状况.结果表明,心理健康问题可以通过网络行为反映出来,通过用户的微博使用情况,预测其抑郁和焦虑的程度是可行的.

关键词: 抑郁, 焦虑, 新浪微博

Abstract:

As generally accepted in clinical psychology,mental health status can be expressed by behavior,including web behavior. Conventional mental health assessment is performed by self-report inventory, and it requires much manual efforts and cannot be done in real time. We aim to objectively predict user's mental health status,especially depression and anxiety. We confirmed the correlation between personality and mental health status in the conventional theory by examining a set of behavior data on sina microblog environment. Multi-task regression is proposed to predict online user's mental health status. The results indicate that mental health disorders are expressed by specific online behaviors and it is possible to predict user's degree of depression and anxiety through his/her microblog usage.

Key words: depression, anxiety, sina microblog

中图分类号: