MoodPupilar: Predicting Mood Through Smartphone Detected Pupillary Responses in Naturalistic Settings
Rahul Islam, Tongze Zhang, Priyanshu Singh Bisen, Sang Won Bae
TL;DR
MoodPupilar tackles objective mood tracking in daily life by mining pupillary responses captured from a smartphone’s front-facing camera. Over four weeks and 470 matched mood days from 25 participants, PIR-based features were extracted from opportunistic eye images and mood labels were computed using the Circumplex Model of Affect; an ensemble with a LightGBM meta-learner was benchmarked on the GLOBEM platform. MoodPupilar achieved $BA=0.63$ and $MCC=0.15$ for valence, and $BA=0.56$ and $MCC=0.12$ for arousal, outperforming several established baselines on GLOBEM in a 5-fold leave-subject-out setting. The work demonstrates the feasibility of real-time, noninvasive mood monitoring in naturalistic contexts, with potential for timely mental health interventions and resource allocation, while also highlighting areas for improvement in data quality, privacy, and cross-modal integration.
Abstract
MoodPupilar introduces a novel method for mood evaluation using pupillary response captured by a smartphone's front-facing camera during daily use. Over a four-week period, data was gathered from 25 participants to develop models capable of predicting daily mood averages. Utilizing the GLOBEM behavior modeling platform, we benchmarked the utility of pupillary response as a predictor for mood. Our proposed model demonstrated a Matthew's Correlation Coefficient (MCC) score of 0.15 for Valence and 0.12 for Arousal, which is on par with or exceeds those achieved by existing behavioral modeling algorithms supported by GLOBEM. This capability to accurately predict mood trends underscores the effectiveness of pupillary response data in providing crucial insights for timely mental health interventions and resource allocation. The outcomes are encouraging, demonstrating the potential of real-time and predictive mood analysis to support mental health interventions.