DeepMood: Modeling Mobile Phone Typing Dynamics for Mood Detection

TL;DR

This paper introduces DeepMood, a deep learning model that predicts mood scores from mobile phone typing dynamics, demonstrating high accuracy and potential for unobtrusive mental health monitoring.

Contribution

The study presents a novel end-to-end deep architecture that effectively models multi-view mobile metadata for mood prediction, advancing digital mental health assessment methods.

Findings

Achieved 90.31% accuracy in depression score prediction

Demonstrated feasibility of using short session typing data for mood inference

Showed potential for unobtrusive mental health monitoring via mobile data

Abstract

The increasing use of electronic forms of communication presents new opportunities in the study of mental health, including the ability to investigate the manifestations of psychiatric diseases unobtrusively and in the setting of patients' daily lives. A pilot study to explore the possible connections between bipolar affective disorder and mobile phone usage was conducted. In this study, participants were provided a mobile phone to use as their primary phone. This phone was loaded with a custom keyboard that collected metadata consisting of keypress entry time and accelerometer movement. Individual character data with the exceptions of the backspace key and space bar were not collected due to privacy concerns. We propose an end-to-end deep architecture based on late fusion, named DeepMood, to model the multi-view metadata for the prediction of mood scores. Experimental results show that 90.31% prediction accuracy on the depression score can be achieved based on session-level mobile phone typing dynamics which is typically less than one minute. It demonstrates the feasibility of using mobile phone metadata to infer mood disturbance and severity.