Adaptive Mobile Personalization Using Social Networks

We present an adaptive personalization system for personalizing news feeds on mobile devices.  The system provides a scroll of news headlines, from which the user may choose to read one or more of the underlying articles. It learns from an individual’s reading history and adapts the news feeds shown to the user. Most importantly, the system automatically discovers new material as a result of shared interests in the user's social network.  The system is based on a text-analysis of the news articles and a Bayes estimator, using only closed form calculations, and runs in real time.  We tested the proposed system using both simulations and a field study in which it was implemented on mobile devices.  We show that using article choices from an individual’s social network improves the quality of personalization, leading to more readership of the news articles provided. The study suggests that utilizing social networks may be a promising avenue for improving personalization of services.