Countering Contextual Bias in TV Watching Behavior: Introducing Social Trend as External Contextual Factor in TV Recommenders

Context-awareness has become a critical factor in improving the predictions of user interest in modern online TV recommendation systems. In addition to individual user preferences, existing context-aware approaches such as tensor factorization incorporate system-level contextual bias to increase predicting accuracy. We analyzed a user interaction dataset from a WebTV platform, and identified that such contextual bias creates a skewed selection of recommended programs which ultimately locks users in a filter bubble. To address this issue, we introduce the Twitter social stream as a source of external context to extend the choice with items related to social media events. We apply two trend indicators, Trend Momentum and SigniScore, to the Twitter histories of relevant programs. The evaluation reveals that Trend Momentum outperforms SigniScore and signalizes 96% of all peaks ahead of time regarding the selected candidate program titles.

[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]  Omar Boussaïd,et al.  Real-time trending topics detection and description from Twitter content , 2015, Social Network Analysis and Mining.

[3]  Ricardo B. C. Prudêncio,et al.  A literature review of recommender systems in the television domain , 2015, Expert Syst. Appl..

[4]  Meng-Jung Shih,et al.  A Context-Aware Recommender System Based on Social Media , 2015 .

[5]  Mario Cataldi,et al.  Emerging topic detection on Twitter based on temporal and social terms evaluation , 2010, MDMKDD '10.

[6]  Jorge García Duque,et al.  What's on tv tonight? An efficient and effective personalized recommender system of TV programs , 2009, 2009 Digest of Technical Papers International Conference on Consumer Electronics.

[7]  Woontack Woo,et al.  Socially aware tv program recommender for multiple viewers , 2009, IEEE Transactions on Consumer Electronics.

[8]  Roberto Pagano,et al.  TV program detection in tweets , 2013, EuroITV.

[9]  Zi Huang,et al.  A temporal context-aware model for user behavior modeling in social media systems , 2014, SIGMOD Conference.

[10]  Duco A. D. Das,et al.  Recommender Systems for TV , 1998 .

[11]  Roberto Turrin,et al.  Performance of recommender algorithms on top-n recommendation tasks , 2010, RecSys '10.

[12]  Damiano Spina.  Entity-based filtering and topic detection For online reputation monitoring in Twitter , 2014 .

[13]  Jorge Ferraz de Abreu,et al.  Viewer behaviors and practices in the (new) television environment , 2013, EuroITV.

[14]  Alexander Tuzhilin,et al.  Comparing context-aware recommender systems in terms of accuracy and diversity , 2012, User Modeling and User-Adapted Interaction.

[15]  Qing Yang,et al.  Trend Analysis of News Topics on Twitter , 2012 .

[16]  Kazutoshi Sumiya,et al.  Towards better TV viewing rates: exploiting crowd's media life logs over Twitter for TV rating , 2011, ICUIMC '11.

[17]  Yutaka Matsuo,et al.  Earthquake shakes Twitter users: real-time event detection by social sensors , 2010, WWW '10.

[18]  Julio Gonzalo,et al.  Learning similarity functions for topic detection in online reputation monitoring , 2014, SIGIR.

[19]  Fernando Díez,et al.  Simple time-biased KNN-based recommendations , 2010, CAMRa '10.

[20]  Thomas Gottron,et al.  Online dating recommender systems: the split-complex number approach , 2012, RSWeb@RecSys.

[21]  Fábio Santos da Silva,et al.  PersonalTVware: a proposal of architecture to support the context-aware personalized recommendation of tv programs , 2009 .

[22]  Bernardo A. Huberman,et al.  Trends in Social Media: Persistence and Decay , 2011, ICWSM.

[23]  Iván Cantador,et al.  Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols , 2013, User Modeling and User-Adapted Interaction.

[24]  Heng Ji,et al.  Identifying News from Tweets , 2016, NLP+CSS@EMNLP.

[25]  Hila Becker,et al.  Hip and trendy: Characterizing emerging trends on Twitter , 2011, J. Assoc. Inf. Sci. Technol..

[26]  José Juan Pazos-Arias,et al.  AVATAR: an improved solution for personalized TV based on semantic inference , 2006, IEEE Transactions on Consumer Electronics.

[27]  Takao Terano,et al.  A TV Program Recommender Framework , 2013, KES.

[28]  Nuria Oliver,et al.  Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering , 2010, RecSys '10.

[29]  Bu-Sung Lee,et al.  Event Detection in Twitter , 2011, ICWSM.

[30]  Rodrygo L. T. Santos,et al.  Context-Aware Event Recommendation in Event-based Social Networks , 2015, RecSys.

[31]  Wei-Po Lee,et al.  A smart TV system with body-gesture control, tag-based rating and context-aware recommendation , 2014, Knowl. Based Syst..

[32]  Juan C. Burguillo,et al.  A hybrid content-based and item-based collaborative filtering approach to recommend TV programs enhanced with singular value decomposition , 2010, Inf. Sci..

[33]  Hans-Peter Kriegel,et al.  SigniTrend: scalable detection of emerging topics in textual streams by hashed significance thresholds , 2014, KDD.

[34]  Matthew Hurst,et al.  Event Detection and Tracking in Social Streams , 2009, ICWSM.

[35]  Roberto Turrin,et al.  A Recommender System for an IPTV Service Provider: a Real Large-Scale Production Environment , 2011, Recommender Systems Handbook.

[36]  Jimeng Sun,et al.  Temporal recommendation on graphs via long- and short-term preference fusion , 2010, KDD.

[37]  Damiano Spina Valentin.  Entity-based filtering and topic detection For online reputation monitoring in Twitter , 2014 .

[38]  Yunming Ye,et al.  Detecting hot topics from Twitter: A multiview approach , 2014, J. Inf. Sci..

[39]  Arkaitz Zubiaga,et al.  Real‐time classification of Twitter trends , 2014, J. Assoc. Inf. Sci. Technol..

[40]  Milan Bjelica,et al.  Context-aware personalized program guide based on neural network , 2012, IEEE Transactions on Consumer Electronics.

[41]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[42]  Charu C. Aggarwal,et al.  Event Detection in Social Streams , 2012, SDM.

[43]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[44]  Nitesh V. Chawla,et al.  Link Prediction and Recommendation across Heterogeneous Social Networks , 2012, 2012 IEEE 12th International Conference on Data Mining.

[45]  Balázs Hidasi,et al.  General factorization framework for context-aware recommendations , 2014, Data Mining and Knowledge Discovery.

[46]  Lora Aroyo,et al.  User model elicitation and enrichment for context-sensitive personalization in a multiplatform tv environment , 2009, EuroITV '09.