PerSummRe: Gaze-Based Personalized Summary Recommendation Tool for Wikipedia

Abstract

The size of Wikipedia grows exponentially every year due to which users face the problem of information overload. The authors propose a remedy to this problem by developing a recommendation system for Wikipedia articles. The proposed technique automatically generates a personalized synopsis of the article that a user aims to read next. They develop a tool, called PerSummRe, which learns the reading preferences of a user through a vision-based analysis of his/her past reads. They use an ensemble non-invasive eye gaze tracking technique to analyze user reading patterns. This tool performs user profiling and generates a recommended personalized summary of yet unread Wikipedia articles for a user. Experimental results showcase the efficiency of the recommendation technique.