Content-Based News Recommendation

The information overloading is one of the serious problems nowadays. We can see it in various domains including business. Especially news represent area where information overload currently prevents effective information gathering on daily basis. This is more significant in connection to the web and news web-based portals, where the quality of the news portal is commonly measured mainly by the amount of news added to the site. Then the most renowned news portals add hundreds of new articles daily. The classical solution usually used to solve the information overload is a recommendation, especially personalized recommendation. In this paper we present an approach for fast content-based news recommendation based on cosine-similarity search and effective representation of the news. We experimented with proposed method in an environment of largest electronic Slovakia newspaper and present results of the experiments.