Activities on Facebook reveal depressive state of users
|
If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL). |
Abstract
â–¶ Background:
Depression, which currently is the most commonly diagnosed mental disorder in many developed countries, is expected to be the second leading cause of disability worldwide by 2020 according to the World Health Organization. Given the growing social interest and the scale of the problem, much effort has been paid toward the early diagnosis, treatment, and prevention of depression. One such effort is to utilize online social network data to reach and detect a large number of individuals with depression at low cost. In doing so, identifying the markers of depression in online social networks is crucial.
â–¶ Objectives:
The goal of this study was to determine depression-related features or activities on the Facebook social network platform, by utilizing a newly developed web application, named EmotionDiary.
â–¶ Methods:
We recruited 55 participants on Facebook, of whom 40 were males aged between 19 and 36 (mean age=24.9±4.4) and 15 were females aged between 19 and 28 (mean age=23.3±2.2). The participants were recruited through both online and offline advertisements made available at the authors’ university. Through the EmotionDiary app, participants could evaluate their depressive symptoms by CES-D (Center for Epidemiological Studies Depression) scale. The app also provided tips about depression and all the profile and activity logs of participants (e.g., Likes, Interests, Viewed tips) were stored for analysis. Correlation analyses were performed between the CES-D scales and the level of various social network activities. Lastly, a psychiatrist interviewed two participants who showed definite depression (CES-D scales were 32 and 25, respectively) to qualitatively assess their symptoms.
â–¶ Results:
Facebook activities had predictive power in distinguishing depressed and non-depressed individuals. Participants’ activities on the app (e.g., the number of viewed tips and points gathered) had a positive correlation with the CES-D scales (P=.04 for both), while the number of Friends and Location tagging had a negative correlation (P=.08 and P=.045, respectively). In terms of group-level markers, the number of viewed tips and points gathered showed a significant difference (P=.01 and P=.03, respectively) in determining the depressed (i.e., CES-D≥21) and non-depressed individuals (i.e., CES-D<21).
â–¶ Conclusions:
Our study demonstrates that while depressed individuals had significantly fewer interpersonal interactions with others (e.g., number of Friends and Location tagging), they were more active in terms of seeking information about depression (e.g., reading tips). These results open the door for utilizing various online social activities in determining depressive symptoms. In the future, we plan to repeat the experiment across multiple cultures.
Depression, which currently is the most commonly diagnosed mental disorder in many developed countries, is expected to be the second leading cause of disability worldwide by 2020 according to the World Health Organization. Given the growing social interest and the scale of the problem, much effort has been paid toward the early diagnosis, treatment, and prevention of depression. One such effort is to utilize online social network data to reach and detect a large number of individuals with depression at low cost. In doing so, identifying the markers of depression in online social networks is crucial.
â–¶ Objectives:
The goal of this study was to determine depression-related features or activities on the Facebook social network platform, by utilizing a newly developed web application, named EmotionDiary.
â–¶ Methods:
We recruited 55 participants on Facebook, of whom 40 were males aged between 19 and 36 (mean age=24.9±4.4) and 15 were females aged between 19 and 28 (mean age=23.3±2.2). The participants were recruited through both online and offline advertisements made available at the authors’ university. Through the EmotionDiary app, participants could evaluate their depressive symptoms by CES-D (Center for Epidemiological Studies Depression) scale. The app also provided tips about depression and all the profile and activity logs of participants (e.g., Likes, Interests, Viewed tips) were stored for analysis. Correlation analyses were performed between the CES-D scales and the level of various social network activities. Lastly, a psychiatrist interviewed two participants who showed definite depression (CES-D scales were 32 and 25, respectively) to qualitatively assess their symptoms.
â–¶ Results:
Facebook activities had predictive power in distinguishing depressed and non-depressed individuals. Participants’ activities on the app (e.g., the number of viewed tips and points gathered) had a positive correlation with the CES-D scales (P=.04 for both), while the number of Friends and Location tagging had a negative correlation (P=.08 and P=.045, respectively). In terms of group-level markers, the number of viewed tips and points gathered showed a significant difference (P=.01 and P=.03, respectively) in determining the depressed (i.e., CES-D≥21) and non-depressed individuals (i.e., CES-D<21).
â–¶ Conclusions:
Our study demonstrates that while depressed individuals had significantly fewer interpersonal interactions with others (e.g., number of Friends and Location tagging), they were more active in terms of seeking information about depression (e.g., reading tips). These results open the door for utilizing various online social activities in determining depressive symptoms. In the future, we plan to repeat the experiment across multiple cultures.
Medicine 2.0® is happy to support and promote other conferences and workshops in this area. Contact us to produce, disseminate and promote your conference or workshop under this label and in this event series. In addition, we are always looking for hosts of future World Congresses. Medicine 2.0® is a registered trademark of JMIR Publications Inc., the leading academic ehealth publisher.
This work is licensed under a Creative Commons Attribution 3.0 License.