Combining Collaborative Filtering and Search Engine into Hybrid News Recommendations

GroupLens used collaborative filtering to generate recommendations for Usenet news and was evaluated by a public trial with users from over a dozen newsgroups. This research identified some important challenges involved in creating a news recommender system. SCENE [15] is such a news service. It stands for a SCal-able two-stage pErsonalized News rEcommendation system. The system considers characteristics such as news content, access patterns, named entities, popularity, and recency of news items when performing recommendation. The proposed news selection mechanism demonstrates the importance of a good balance between user interests, the novelty, and diversity of the recommendations. The News@hand system [5] is a news recommender which applies semantic-based technologies to describe and relate news contents and user preferences in order to produce enhanced recommendations. This news system ensures multi-media source applicability. The resultant recommendations can be adapted to the current context of interest, thereby emphasizing the importance of contextualization in the domain of news. In the CLEF NEWSREEL track [3], news recommendation techniques could be evaluated in real-time by providing news recommendations to actual users that visit commercial news portals. A web-based platform is used to distribute recommendations to the users and return users' impressions of the recommendations to the researchers. The News Recommender Systems Challenge [22] focused on providing live recommendations for readers of German news media articles. This challenge highlighted why news recommendations have not been analyzed as thoroughly as some of the other domains such as movies, books, or music. Reasons for this include the lack of data sets as well as the lack of open systems to deploy algorithms in. In the challenge, the deployed recommenders for generating news recommendations are: Recent Recommender (based only on the recency of the articles), Lucene Recommender (a text retrieval system built on top of Apache Lucene), Category-based Recommender (using the article's category), User Filter (filters out the articles previously observed by the current user), and Combined Recommender (a stack or cascade of two or more of the above recommenders). The usefulness of retrieval algorithms for content-based recommendations has been demonstrated with experiments using a large data set of news content [2]. Binary and graded evaluation were compared and graded evaluation showed to be intrinsically better for news recommendations. This study emphasizes the potential of combining content-based approaches with collaborative filtering into a hybrid recom-mender system for news. Although the various initiatives emphasize the importance of a personalized news offer, …