Identifying depression related behaviour in Facebook – an experimental study

Zoltán Kmetty, Károly Bozsonyi

Contact: zkmetty@yahoo.com

Recently several studies have been published investigating the possible relationships between the spread of suicides/mental problems in society and Internet use. Most of the studies focus on aggregate level behaviour and patterns, how people use some keywords or certain hashtags. There are some studies that analyse the relationship between Facebook activity and depression, but as far as we know, there is no any study which use “real” Facebook usage data for this purpose. Our study uses a novel joint datasource of combined Facebook and survey data. After an informed consent obtained, respondents were asked to log-in to FB on the interviewers’ notebook and to download their FB profile archive. 150 respondents took part in our study. the data covers a wide range of Facebook activities: posts, comments, likes and reactions, pages, friends, profile, and ads data. The full friend list contains 116 000 names (anonymized), there are 83 000 page-like from more than 50 000 unique pages, and the database contains more than 1 800 000 reactions as well as all posts and comments of the participants. The data covers the whole time period of the participants’ Facebook usage. Besides sharing their Facebook data, participants had to fill out an online questionnaire. Questions about politics, media usage, self-representation. spare-time activities and music preferences were asked from the participants. Above that, we asked the participants to fill out a modified version of Patient Helath Questionnaire (PHQ-9). In this study we use this slightly modified PHQ-9 questionnaire module. Two indicators of depression are extracted by ML Factor Analysis based on the PHQ-9 questions, a cognitive and a psychosomatic one. We analyse the relationship between these indicators and the logged behaviour of respondents in Facebook. We extract several dimension of FB usage, we calculate the burstiness of activities, the size of core network of the respondent, the change of core network and some measures based of FB page likes. The study helps us to understand better how depression could be identified through social media usage.

→PDF

  

← Schedule