Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data
This addresses the need for early detection of mental health issues in high-risk adolescent populations using mobile data, but it is incremental as it builds on existing privacy-preserving methods.
The paper tackled the problem of predicting daily mood from mobile data while preserving user privacy, finding that language and multimodal representations are predictive but also capture private identities, and by combining these with privacy-preserving learning, they advanced the performance-privacy trade-off.
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.