NewsRec, a SVM-driven Personal Recommendation System for News Websites

Fast absorption of information is a necessity for modern information workers. In the short-lived news area, information is a perishable good. While online news websites can speed up the publication of current events compared to traditional newspapers, reading can be more exhausting as online readers have to navigate through websites by clicking on abstracts or headlines before viewing the underlying article. Online shops use personalization methods in order to improve product selection. So far, most types of personalization are offered by website owners and are therefore bound to a specific website. This work presents NewsRec, a client side personal recommendation system for news websites, that supports information workers during their usage of online news websites. Design aspects are discussed and empirical results are shown.