Messenger Use and Video Calls as Correlates of Depressive andAnxiety Symptoms:Results From the Corona Health App Studyof German Adults During the COVID-19 Pandemic

Background: Specialized studies have shown that smartphone-based social interaction data are predictors of depressive andanxiety symptoms. Moreover, at times during the COVID-19 pandemic, social interaction took place primarily remotely. Toappropriately test these objective data for their added value for epidemiological research during the pandemic, it is necessary toinclude established predictors. Objective: Using a comprehensive model, we investigated the extent to which smartphone-based social interaction data contributeto the prediction of depressive and anxiety symptoms, while also taking into account well-established predictors and relevantpandemic-specific factors. Methods: We developed the Corona Health App and obtained participation from 490 Android smartphone users who agreedto allow us to collect smartphone-based social interaction data between July 2020 and February 2021. Using a cross-sectionaldesign, we automatically collected data concerning average app use in terms of the categories video calls and telephony, messengeruse, social media use, and SMS text messaging use, as well as pandemic-specific predictors and sociodemographic covariates.We statistically predicted depressive and anxiety symptoms using elastic net regression. To exclude overfitting, we used 10-foldcross-validation. Results: The amount of variance explained (R2) was 0.61 for the prediction of depressive symptoms and 0.57 for the predictionof anxiety symptoms. Of the smartphone-based social interaction data included, only messenger use proved to be a significantnegative predictor of depressive and anxiety symptoms. Video calls were negative predictors only for depressive symptoms, andSMS text messaging use was a negative predictor only for anxiety symptoms. Conclusions: The results show the relevance of smartphone-based social interaction data in predicting depressive and anxietysymptoms. However, even taken together in the context of a comprehensive model with well-established predictors, the data onlyadd a small amount of value