Digital Footprints: Predicting Personality from Temporal Patterns of Technology Use

Psychometric modeling using digital data traces is a growing field of research with a breadth of potential applications in marketing, personalization and psychological assessment. We present a novel form of digital traces for user modeling: temporal patterns of smartphone and personal computer activity. We show that some temporal activity metrics are highly correlated with certain Big Five personality metrics. We then present a machine learning method for binary classification of each Big Five personality trait using these temporal activity patterns of both computer and smartphones as model features. Our initial findings suggest that Extroversion, Openness, Agreeableness, and Neuroticism can be classified using temporal patterns of digital traces at a similar accuracy to previous research that classified personality traits using different types of digital traces.