Depression Detection from Social Media Texts

Authors

Grigoriev O. Smirnoff I. Stankevich M.

Annotation

The problem of early depression detection is one of the most important in the field of psychology. Social network analysis is widely applied to address this problem. In this paper, we consider the task of automatic detection of depression signs from textual messages and profile information of Russian social network VKontakte users. We describe the preparation of users’ profiles dataset and propose linguistic and profile information based features. We evaluate several machine learning methods and report experiments results. The best performance in our experiments achieved by the model that was trained on features that reflects information about users’ subscriptions on Vkontakte groups and communities.

External links

PDF at the CEUR Workshop Proceedings journal website: ceur-ws.org/Vol-2523/paper26.pdf

Read or download PDF at SpringerLink: https://link.springer.com/chapter/10.1007/978-3-030-51913-1_12

RUDN University. Repository: https://repository.rudn.ru/en/records/article/record/56473/

Reference link

Stankevich M., Latyshev A., Kuminskaya E., Smirnov I., Grigoriev O. Depression Detection from Social Media Texts // Selected Papers of the XXI International Conference on Data Analytics and Management in Data Intensive Domains (DAMDID/RCDL 2019), 2019, pp. 279-289.