A demographic study of depression analysis in india using social media

Abstract

Mental illness is one of the most pressing public health issues of our time. The pervasiveness of social media and the near-ubiquity of mobile devices used to access social media networks offer new types of data for understanding the behaviour of people. Depression is typically diagnosed as being present or absent. However, depression severity is believed to be continuously distributed rather than dichotomous. In this work, we focus on applying natural language processing (NLP) techniques to analyse tweets in terms of Depression. In this study we have analyzed 3,44,300 tweets using geolocation feature from 25 different cities in India. We trained deep models that measure depression score of each tweet ranging from 0 to 1. From the tweet-level depression scores, we computed user-level depression scores and city-specific depression index. Furthermore, we collected the census data of India for all these cities and studied the relationship between depression and the socio-economic factors recorded in the census data. The study gives us important insights about the reasons that are causing depression.