Examining the Correlation Between Depression and Social Behavior on Smartphones Through Usage Metadata: Empirical...

Area of Science:

• Digital phenotyping
• Psychiatry
• Human-computer interaction

Background:

• Smartphone use is pervasive, offering new avenues for objective mental health research.
• Traditional depression assessment relies on subjective self-report questionnaires.
• Digital data provides novel insights into individual differences and mental health conditions.

Purpose of the Study:

• To investigate the digital social behavior of depressed Chinese individuals using smartphone metadata.
• To explore correlations between depression and smartphone-based social interactions.

Main Methods:

• 120 participants used a smartphone app (MobileSens) for metadata collection.
• Participants completed the Center for Epidemiological Studies-Depression Scale (CES-D) for depression assessment.
• Extracted 44 smartphone usage features, including calls, SMS, and social app usage (WeChat, Sina Weibo).
• Statistical analyses included 2-way ANOVA and multiple logistic regression.

Main Results:

• Depressed users received fewer calls and used social apps more frequently than non-depressed users.
• Depressed females showed higher Weibo usage than males.
• Evening social app usage predicted depressive symptoms in all participants and males.
• Morning Weibo usage predicted depressive symptoms in females.

Conclusions:

• Smartphone social behavior is correlated with depression.
• Findings can inform interventions to improve social interaction for depressed individuals.
• Results offer potential for early depression diagnosis using digital behavioral data.