Auto-Tagging User Traits in the Context of Smartphones

Abstract

In the past few decades research has been done on the prediction of personality traits of users from social media to enhance users experience while using social media applications. Most often we tend to be more upfront with our smartphones and personalise it to suit our daily moods and emotions. These sensor-rich devices can easily be repurposed to collect rich and extensive records of their users’ behaviour. Questionnaire based personality tests pose certain challenges as test takers may not be able to accurately answer the questions due to various personal or professional reasons on a survey. Employing a methodology based in the context of smartphone application usage data is an attempt to increase the accuracy in identifying the user’s personality traits as this data will be more closely related to the user’s changing behavioural pattern over a set of time periods.