Recognizing depression of social media users from their records of activities

2015 Fiscal Year Final Research Report

• Project/Area Number: 26870076
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Multimedia database; Web informatics, Service informatics
• Research Institution: University of Tsukuba
• Principal Investigator: Tsugawa Sho 筑波大学, システム情報系, 助教 (40632732)
• Project Period (FY): 2014-04-01 – 2016-03-31
• Keywords: ソーシャルメディア / うつ / 機械学習 / Twitter

Outline of Final Research Achievements

In recent years, depression is one of significant problems in the world. For the effective treatment of depression, it is important to recognize depressive tendencies of individuals. This study constructed several models to estimate depressive tendency of social media users from the features obtained from user's activities. Through experiments, we showed that using the records of user's activities is effective for recognizing depression. We also showed effective features for recognizing depression of social media users, and the relation between the length of the training period for constructing the models and their estimation accuracy.

Free Research Field

ネットワーク科学