Personality Trait Inference Via Mobile Phone Sensors: A Machine Learning Approach
Wun Yung Shaney Sze, Maryglen Pearl Herrero, Roger Garriga
TL;DR
This work addresses inferring the Big Five personality traits from passive mobile sensing without questionnaires. It extracts $83$ accelerometer-based features from $144$ iPhone users, applies Recursive Feature Elimination with Cross-Validation to create trait-specific feature subsets, and trains Random Forest and XGBoost classifiers for binary ($50^{th}$ percentile) and multiclass ($33^{rd}$/$67^{th}$ percentile) targets under stratified k-fold CV with Bayesian hyperparameter optimization. Binary prediction achieves $F1$ scores from $0.56$ to $0.78$, with Extraversion reaching $0.78$, while multiclass performance ranges from $0.25$ to $0.47$, with Openness at $0.47$; the models reveal trait-specific behavioral correlates such as outdoor activity for Extraversion and sleep/weekend activity for Openness. The findings demonstrate the potential and limitations of scalable, questionnaire-free personality assessment using ubiquitous sensor data, highlighting practical implications for organizational and research contexts while underscoring generalizability concerns beyond a student population.
Abstract
This study provides evidence that personality can be reliably predicted from activity data collected through mobile phone sensors. Employing a set of well informed indicators calculable from accelerometer records and movement patterns, we were able to predict users' personality up to a 0.78 F1 score on a two class problem. Given the fast growing number of data collected from mobile phones, our novel personality indicators open the door to exciting avenues for future research in social sciences. Our results reveal distinct behavioral patterns that proved to be differentially predictive of big five personality traits. They potentially enable cost effective, questionnaire free investigation of personality related questions at an unprecedented scale. We show how a combination of rich behavioral data obtained with smartphone sensing and the use of machine learning techniques can help to advance personality research and can inform both practitioners and researchers about the different behavioral patterns of personality. These findings have practical implications for organizations harnessing mobile sensor data for personality assessment, guiding the refinement of more precise and efficient prediction models in the future.