Text-based experiments for Predicting mental health emergencies in online web forum posts

Hector-Hugo Franco-Penya, Liliana Mamani Sanchez
2016 Proceedings of the Third Workshop on Computational Lingusitics and Clinical Psychology  
This article explores how to build a system for detecting users in a need of attention on ReachOut.com forums. The proposed method uses Tree Kernels over binary Support Vector Machines classification and linear regression, comparing these two machine learning techniques. Predictions from one of these systems were submitted to the CLPsych 2016 Shared Task. Nonetheless, results indicate that it is possible to build an accurate system using only text features without the use of other meta data.
doi:10.18653/v1/w16-0327 dblp:conf/naacl/Franco-PenyaS16 fatcat:khg6iregsjd2him4kmxpzgphpi