Phone call log as a context source to modeling individual user behavior

Abstract

Mobile phone can record various types of context data related to a user's phone call activities in its call log. Call log provides temporal context to modeling individual user's phone call response behavior, i.e., when a user accepts, rejects or misses an incoming call. In this paper, we explore the potentiality of phone call log as a context source to modeling call response behavior of individual mobile users. Towards this, we present our initial work to generating temporal rules that capture the user's dominant call response behavior at various times of the day and days of the week, utilizing phone call log. Our preliminary experimental results on real datasets show that context information in call log can be used to model individual's phone call response behavior with high accuracy.