MoodCam: Mood Prediction Through Smartphone-Based Facial Affect Analysis in Real-World Settings

TL;DR

MoodCam leverages smartphone facial affect analysis to predict mood in real-world settings, enabling timely mental health interventions with models achieving moderate accuracy in mood trend forecasting.

Contribution

This study introduces a novel smartphone-based facial affect analysis method for real-time mood prediction during everyday activities, with models demonstrating effective mood trend forecasting.

Findings

Models achieved AUC scores of 0.58-0.64 for Valence and 0.60-0.63 for Arousal.

Facial behavior primitives can predict mood with moderate accuracy.

Real-world data collection over four weeks from 25 participants.

Abstract

MoodCam introduces a novel method for assessing mood by utilizing facial affect analysis through the front-facing camera of smartphones during everyday activities. We collected facial behavior primitives during 15,995 real-world phone interactions involving 25 participants over four weeks. We developed three models for timely intervention: momentary, daily average, and next day average. Notably, our models exhibit AUC scores ranging from 0.58 to 0.64 for Valence and 0.60 to 0.63 for Arousal. These scores are comparable to or better than those from some previous studies. This predictive ability suggests that MoodCam can effectively forecast mood trends, providing valuable insights for timely interventions and resource planning in mental health management. The results are promising as they demonstrate the viability of using real-time and predictive mood analysis to aid in mental health interventions and potentially offer preemptive support during critical periods identified through mood trend shifts.