Predicting Depression for Japanese Blog Text

Misato Hiraga
2017 Proceedings of ACL 2017, Student Research Workshop  
This study aims to predict clinical depression, a prevalent mental disorder, from blog posts written in Japanese by using machine learning approaches. The study focuses on how data quality and various types of linguistic features (characters, tokens, and lemmas) affect prediction outcome. Depression prediction achieved 95.5% accuracy using selected lemmas as features.
doi:10.18653/v1/p17-3018 dblp:conf/acl/Hiraga17 fatcat:jlkivaodtncd5kirgt7qmcqlpe