Depression detection from social media profiles

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. © Springer Nature Switzerland AG 2020.

Авторы
Stankevich M. 1 , Smirnov I. 1, 2 , Kiselnikova N.3 , Ushakova A.4
Сборник материалов конференции
Издательство
Springer Verlag
Язык
Английский
Страницы
181-194
Статус
Опубликовано
Том
1223 CCIS
Год
2020
Организации
  • 1 Federal Research Center “Computer Science and Control” of RAS, Moscow, Russian Federation
  • 2 Peoples’ Friendship University of Russia (RUDN University), Moscow, Russian Federation
  • 3 Psychological Institute, Russian Academy of Education, Moscow, Russian Federation
  • 4 Moscow Institute of Physics and Technology, Moscow, Russian Federation
Ключевые слова
Depression detection; Psycholinguistics; Social networks
Дата создания
02.11.2020
Дата изменения
02.11.2020
Постоянная ссылка
https://repository.rudn.ru/ru/records/article/record/65568/