Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data

TL;DR

This study explores how language and multimodal data from smartphones can predict daily mood in adolescents at high risk of suicidal behaviors, while also addressing privacy concerns through obfuscation techniques.

Contribution

It introduces methods to predict mood from mobile data and proposes privacy-preserving approaches to prevent user identification.

Findings

Multimodal mobile data can predict daily mood effectively.

Models often inadvertently reveal user identities.

Privacy-preserving methods can maintain mood prediction accuracy.

Abstract

Mental health conditions remain underdiagnosed even in countries with common access to advanced medical care. The ability to accurately and efficiently predict mood from easily collectible data has several important implications for the early detection, intervention, and treatment of mental health disorders. One promising data source to help monitor human behavior is daily smartphone usage. However, care must be taken to summarize behaviors without identifying the user through personal (e.g., personally identifiable information) or protected (e.g., race, gender) attributes. In this paper, we study behavioral markers of daily mood using a recent dataset of mobile behaviors from adolescent populations at high risk of suicidal behaviors. Using computational models, we find that language and multimodal representations of mobile typed text (spanning typed characters, words, keystroke timings, and app usage) are predictive of daily mood. However, we find that models trained to predict mood often also capture private user identities in their intermediate representations. To tackle this problem, we evaluate approaches that obfuscate user identity while remaining predictive. By combining multimodal representations with privacy-preserving learning, we are able to push forward the performance-privacy frontier.