Activities on Facebook reveal depressive state of users

Sungkyu Park, MS; Sang Won Lee, MD; Jinah Kwak, MS; Meeyoung Cha, PhD; Bumseok Jeong, MD, PhD

Full paper accepted at Journal of Medical Internet Research (JMIR), August 2013

fig1_rev20130515

Abstract

Background: As online social media have become prominent, much effort has been paid to identifying users with depressive symptoms to aim at early diagnosis, treatment, and even prevention by utilizing various online social media. In this paper we focused on the particular social media, Facebook, to discern any correlations between Facebook features and depressive symptoms. This attempt may be helpful to reach and detect large numbers of depressive individuals with ease.

Objective: Our goal was to develop a web application and identify depressive-symptom-related features from users of Facebook, a popular platform of online social network.

Methods: 55 Facebook users (male = 40, female = 15, mean age = 24.43 ± 3.90) were recruited through advertisement fliers distributed to students in a large university in Korea. Using EmotionDiary, the Facebook application we developed, we evaluated depressive symptoms using the Center for Epidemiological Studies-Depression (CES-D) scale. We also provided tips and facts about depression to participants and measured their responses using EmotionDiary. To identify the Facebook features related to depression, correlation analyses were performed between CES-D and participants’ responses to tips and facts or Facebook social features. Lastly, we interviewed depressed participants (CES-D ≥ 25) to assess their depressive symptoms by a psychiatrist.

Results: Facebook activities had predictive power in distinguishing depressed and non-depressed individuals. Participants’ response to tips and facts, which can be explained by the number of app tips viewed and app points, had a positive correlation (P = .04 for both cases) whereas the number of friends and location tagging had a negative correlation with the CES-D scale (P = .08 and P = .045 respectively). Furthermore, in finding group differences in Facebook social activities, app tips viewed and app points resulted in significant differences (P = .01 and P = .03 respectively) between probably depressed and non-depressed individuals.

Conclusions: Our results using EmotionDiary demonstrated that the more one is depressed, the more one will read tips and facts about depression. We also confirmed depressed individuals had significantly fewer interactions with others (e.g., decreased number of friends and location tagging). Our app can successfully evaluate depressive symptoms as well as provide useful tips and facts. These results open the door for examining Facebook activities to identify depressed individuals. We aim to conduct the experiment in multiple cultures as well.

Keywords

Facebook; Web application; Depressive symptoms; OSN activities; Mental health; Internet

 

[pdf] download

[source code] link to GitHub (available soon! → should you have any questions or requests regarding the code, please e-mail to shaun.park [at] kaist.ac.kr)

[KAIST IRB] 인간대상 연구 동의서 서식

 

 

Appendix1_flowchart_rev130731

2 Trackbacks

  1. [...] The main theme of this paper is to determine the extent to which certain user-generated contents in OSN are reflective of users’ clinical depressive states. We collaborated with the psychiatrists of Graduate School of Medical Science and Engineering at KAIST. For more detailed information regarding this work, please visit the following link: [here] [...]

  2. By pembicara internet marketing on 2월 17, 2014 at 3:35 오전

    …Trackback: More Informations on that topic…

    [...]The whole look of your web site is fantastic, let well as the content material![...]…