论文信息 - News Recommendation

News Recommendation

News recommendation systems allow selecting, from an immense offer, only the news the users are interest on. Nowadays state-of-art distinguishes three types of recommendation systems: systems based on content, collaborative systems and hybrid systems. The Weighted Slope (WSO) is an algorithm that follows the collaborative approach that has been used in several domains. This article proposes an extension of the WSO that will improve the algorithm performance, in order to recommend news, through the introduction of new features, related to the similarity and to the news source. The general performances of both, proposed and WSO algorithms, were evaluated. Other from that we have also analyzed the performances on critical cases like new users, new news and multimedia formatted news. Every experiment reveals that the proposed algorithm allows improving the performance of original WSO. All tests were performed on a collection of news developed on the current project.

R. D. Santos | Romenigue dos Santos

[1] John Riedl,et al. GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[2] Daniel Lemire,et al. Slope One Predictors for Online Rating-Based Collaborative Filtering , 2007, SDM.

[3] Yoav Shoham,et al. Fab: content-based, collaborative recommendation , 1997, CACM.

[4] Abhinandan Das,et al. Google news personalization: scalable online collaborative filtering , 2007, WWW '07.

[5] Zhaohui Zheng,et al. Learning to model relatedness for news recommendation , 2011, WWW.

[6] John Riedl,et al. Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[7] Ken Lang,et al. NewsWeeder: Learning to Filter Netnews , 1995, ICML.

[8] Michael J. Pazzani,et al. A learning agent for wireless news access , 2000, IUI '00.

[9] Gediminas Adomavicius,et al. Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[10] Mark Claypool,et al. Combining Content-Based and Collaborative Filters in an Online Newspaper , 1999, SIGIR 1999.

[11] Douglas W. Oard,et al. Implicit Feedback for Recommender Systems , 1998 .

[12] Antal van den Bosch,et al. Comparing and evaluating information retrieval algorithms for news recommendation , 2007, RecSys '07.