Recommending Personalized News in Short User Sessions

News organizations employ personalized recommenders to target news articles to specific readers and thus foster engagement. Existing approaches rely on extensive user profiles. However frequently possible, readers rarely authenticate themselves on news publishers' websites. This paper proposes an approach for such cases. It provides a basic degree of personalization while complying with the key characteristics of news recommendation including news popularity, recency, and the dynamics of reading behavior. We extend existing research on the dynamics of news reading behavior by focusing both on the progress of reading interests over time and their relations. Reading interests are considered in three levels: short-, medium-, and long-term. Combinations of these are evaluated in terms of added value to the recommendation's performance and ensured news variety. Experiments with 17-month worth of logs from a German news publisher show that most frequent relations between news reading interests are constant in time but their probabilities change. Recommendations based on combined short-term and long-term interests result in increased accuracy while recommendations based on combined short-term and medium-term interests yield higher news variety.

[1]  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.

[2]  Pasquale Lops,et al.  Semantics-Aware Content-Based Recommender Systems , 2014, Recommender Systems Handbook.

[3]  Tao Li,et al.  Product recommendation with temporal dynamics , 2012, Expert Syst. Appl..

[4]  Guy Shani,et al.  An MDP-Based Recommender System , 2002, J. Mach. Learn. Res..

[5]  Boi Faltings,et al.  Personalized News Recommendation Based on Collaborative Filtering , 2012, 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

[6]  Aonghus Lawlor,et al.  An Analysis of Recommender Algorithms for Online News , 2014, CLEF.

[7]  Jianyong Wang,et al.  Personalizing Web Page Recommendation via Collaborative Filtering and Topic-Aware Markov Model , 2010, 2010 IEEE International Conference on Data Mining.

[8]  Frank Hopfgartner,et al.  Users' reading habits in online news portals , 2014, IIiX.

[9]  Qi Gao,et al.  Interweaving Trend and User Modeling for Personalized News Recommendation , 2011, 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

[10]  Eelco Herder,et al.  Timeline Summarization from Relevant Headlines , 2015, ECIR.

[11]  Susan Gauch,et al.  Incorporating popularity in a personalized news recommender system , 2016, PeerJ Comput. Sci..

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

[13]  Param Vir Singh,et al.  A Hidden Markov Model for Collaborative Filtering , 2010, MIS Q..

[14]  Gilad Kutiel,et al.  Effective Trend Detection within a Dynamic Search Context , 2016, SIGIR.

[15]  Diyi Yang,et al.  Local implicit feedback mining for music recommendation , 2012, RecSys.

[16]  Chava Nachmias,et al.  Social statistics for a diverse society , 2009 .

[17]  Andreas Lommatzsch,et al.  Real-Time News Recommendation Using Context-Aware Ensembles , 2014, ECIR.

[18]  Xindong Wu,et al.  Personalized News Filtering and Summarization on the Web , 2011, 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence.

[19]  B. Nordstrom.  FINITE MARKOV CHAINS , 2005 .

[20]  Wei Chu,et al.  A contextual-bandit approach to personalized news article recommendation , 2010, WWW '10.

[21]  Yong Liu,et al.  Improved Recurrent Neural Networks for Session-based Recommendations , 2016, DLRS@RecSys.

[22]  Flavius Frasincar,et al.  Semantic news recommendation using wordnet and bing similarities , 2013, SAC '13.

[23]  Ting-Peng Liang,et al.  Discovering user interests from Web browsing behavior: an application to Internet news services , 2002, Proceedings of the 35th Annual Hawaii International Conference on System Sciences.

[24]  Alexander J. Smola,et al.  Fair and balanced: learning to present news stories , 2012, WSDM '12.

[25]  Barry Smyth,et al.  Using twitter to recommend real-time topical news , 2009, RecSys '09.

[26]  Jiahui Liu,et al.  Personalized news recommendation based on click behavior , 2010, IUI '10.

[27]  Mahdi Jalili,et al.  A probabilistic model to resolve diversity–accuracy challenge of recommendation systems , 2015, Knowledge and Information Systems.

[28]  John G. Kemeny,et al.  Finite Markov Chains. , 1960 .

[29]  Anirban Mahanti,et al.  Characterizing and Predicting Viral-and-Popular Video Content , 2015, CIKM.

[30]  Jon Espen Ingvaldsen,et al.  Process mining for recommender strategies support in news media , 2016, 2016 IEEE Tenth International Conference on Research Challenges in Information Science (RCIS).

[31]  Frank Bickenbach,et al.  Evaluating the Markov Property in Studies of Economic Convergence , 2003 .

[32]  Jon Atle Gulla,et al.  3rd International Workshop on News Recommendation and Analytics (INRA 2015) , 2015, RecSys.

[33]  Emily Thorson,et al.  CHANGING PATTERNS OF NEWS CONSUMPTION AND PARTICIPATION , 2008 .

[34]  Karima Saleh,et al.  Overview and key findings , 2018, World Energy Outlook 2018.

[35]  Fan Yang,et al.  Modeling and broadening temporal user interest in personalized news recommendation , 2014, Expert Syst. Appl..

[36]  Aristides Gionis,et al.  From chatter to headlines: harnessing the real-time web for personalized news recommendation , 2012, WSDM '12.

[37]  Alexandros Karatzoglou,et al.  Session-based Recommendations with Recurrent Neural Networks , 2015, ICLR.

[38]  Michael J. Pazzani,et al.  Adaptive News Access , 2007, The Adaptive Web.