Capturing mood dynamics through adolescent smartphone social communication.

Abstract

Most adolescents with depression remain undiagnosed and untreated—missed opportunities that are costly from both personal and public health perspectives. A promising approach to detecting adolescent depression in real-time and at a large scale is through their social communication on the smartphone (e.g., text messages, social media posts). Past research has shown that language from online social communication reliably indicates interindividual differences in depression. To move toward detecting the emergence of depression symptoms intraindividually, the present study tested whether sentiment (i.e., words connoting positive and negative affect) from smartphone social communication prospectively predicted daily mood fluctuations in 83 adolescents (Mage = 16.49, 73.5% female) with a wide range of depression severity. Participants completed daily mood ratings across a 90-day period, during which 354,278 messages were passively collected from social communication apps. Greater positive sentiment (i.e., more positive weighted composite valence score and a greater proportion of words expressing positive sentiment) predicted more positive next-day mood, controlling for previous-day mood. Moreover, greater proportions of positive and negative sentiment were, respectively, associated with lower anhedonia and greater dysphoria symptoms measured at baseline. Exploratory analyses of nonaffective linguistic features showed that greater use of social engagement words (e.g., friends and affiliation) and emojis (primarily consisting of hearts) predicted more positive changes in mood. Collectively, findings suggest that language from smartphone social communication can detect mood fluctuations in adolescents, laying the foundation for language-based tools to identify periods of heightened depression risk.

Detecting Adolescent Depression Through Passive Monitoring of Linguistic Markers in Smartphone Communication

“…Exploratory analyses of data-driven LDA topics revealed that a language topic reflecting feelings was associated with increased risk for concurrent MDD, extending cross-sectional research linking feelings-related words to depression (Li et al, 2023;Liu et al, 2022;Stamatis et al, 2022;Tølbøll, 2019). Additionally, less judgment -a topic primarily reflecting positive and negative appraisals (e.g., funny, stupid) -was associated with greater MDD risk.…”

“…We used each app's classification and description in the Apple App Store and/or Google Play Store to determine whether it was primarily for social communication (Li et al, 2023;McNeilly et al, 2023). The most used social communication apps were messaging (e.g., Messaging, Discord, Kakao) and social media apps (e.g., Snapchat, Instagram; see Figure S1 for a list of all included apps).…”

“…The few studies examining within-person associations between linguistic features and depression suggest that more negative sentiment and first-person singular pronouns in digital communication may predict greater depressive symptoms in adults (Nook et al, 2022;Stamatis et al, 2022). No research in adolescents has studied within-person links between linguistic features and depression, and while several studies have investigated associations between adolescents' linguistic features and daily mood, findings have been mixed (Kross et al, 2019;Li et al, 2023;McNeilly et al, 2023). Taken together, elucidating within-person associations between smartphone communication and adolescent depression could inform dynamic risk prediction models and offer a novel opportunity for more timely intervention during a high-risk developmental period.…”

“…LDA topics may afford unique insights into adolescents' smartphone communication, as they could contain communication types that are difficult to include in predefined dictionaries (e.g., misspellings, slang). Notably, preliminary research has shown that certain LDA-derived topics (e.g., loneliness) in digital communication related to depression (Eichstaedt et al, 2018;Li et al, 2023).…”

The effects of family support and smartphone-derived homestay on daily mood and depression among sexual and gender minority adolescents.

“…Adolescents (ages 13-18 years old; N = 148) were recruited from the greater New York City and Chicago communities through social media advertisements, as part of a multisite longitudinal study of social processes in adolescent depression (Li et al, 2023). No SGM-targeted recruitment strategies were employed.…”