Activities on Facebook Reveal the Depressive State of Users

• DOI: 10.2196/jmir.2718
• Publication Date: 2013-10-01T15:39:30Z
• Authors: Sungkyu Park; Sang Won Lee; Jinah Kwak; Meeyoung Cha; Bumseok Jeong
• Keywords: Adult; Male; Original Paper; Internet; Depression; Computer applications to medicine. Medical informatics; 150; R858-859.7; Facebook; Web application; depressive symptoms; online social network(OSN) activities; mental health; Internet; 03 medical and health sciences; 0302 clinical medicine; Republic of Korea; Humans; Female; Public aspects of medicine; RA1-1270; Social Media

Background: As online social media have become prominent, much effort has been spent on identifying users with depressive symptoms in order to aim at early diagnosis, treatment, and even prevention by using various media. In this paper, we focused Facebook discern any correlations between the platform's features users' symptoms. This work may be helpful trying reach detect large numbers of depressed individuals more easily. Objective: Our goal was develop a Web application identify symptom–related from Facebook, popular networking platform. Methods: 55 (male=40, female=15, mean age 24.43, SD 3.90) were recruited through advertisement fliers distributed students university Korea. Using EmotionDiary, developed, evaluated Center for Epidemiological Studies-Depression (CES-D) scale. We also provided tips facts about depression participants measured their responses EmotionDiary. To related depression, correlation analyses performed CES-D participants' or features. Last, interviewed (CES-D≥25) assess psychiatrist. Results: activities had predictive power distinguishing nondepressed individuals. Participants' response facts, which can explained number app viewed points, positive (P=.04 both cases), whereas friends location tags negative scale (P=.08 P=.045 respectively). Furthermore, finding group differences activities, points resulted significant (P=.01 P=.03 respectively) probably Conclusions: results EmotionDiary demonstrated that one is, will read depression. confirmed significantly fewer interactions others (eg, decreased tagging). app, successfully evaluate as well provide useful users. These open door examining conduct experiment multiple cultures well.