Immersive Recommendation: News and Event Recommendations Using Personal Digital Traces

We propose a new user-centric recommendation model, called Immersive Recommendation, that incorporates cross-platform and diverse personal digital traces into recommendations. Our context-aware topic modeling algorithm systematically profiles users' interests based on their traces from different contexts, and our hybrid recommendation algorithm makes high-quality recommendations by fusing users' personal profiles, item profiles, and existing ratings. Specifically, in this work we target personalized news and local event recommendations for their utility and societal importance. We evaluated the model with a large-scale offline evaluation leveraging users' public Twitter traces. In addition, we conducted a direct evaluation of the model's recommendations in a 33-participant study using Twitter, Facebook and email traces. In the both cases, the proposed model showed significant improvement over the state-of-the-art algorithms, suggesting the value of using this new user-centric recommendation model to improve recommendation quality, including in cold-start situations.

[1]  Chong Wang,et al.  Collaborative topic modeling for recommending scientific articles , 2011, KDD.

[2]  Michael R. Lyu,et al.  SoRec: social recommendation using probabilistic matrix factorization , 2008, CIKM '08.

[3]  Krishna P. Gummadi,et al.  Inferring user interests in the Twitter social network , 2014, RecSys '14.

[4]  Chiranjib Bhattacharyya,et al.  Content Driven User Profiling for Comment-Worthy Recommendations of News and Blog Articles , 2015, RecSys.

[5]  Fabrizio Silvestri,et al.  Making your interests follow you on twitter , 2012, CIKM.

[6]  Bei Yu,et al.  A cross-collection mixture model for comparative text mining , 2004, KDD.

[7]  Michael J. Paul,et al.  Cross-Cultural Analysis of Blogs and Forums with Mixed-Collection Topic Models , 2009, EMNLP.

[8]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[9]  Zhe Zhao,et al.  Improving User Topic Interest Profiles by Behavior Factorization , 2015, WWW.

[10]  Deepak Agarwal,et al.  fLDA: matrix factorization through latent dirichlet allocation , 2010, WSDM '10.

[11]  Hugo Zaragoza,et al.  The Probabilistic Relevance Framework: BM25 and Beyond , 2009, Found. Trends Inf. Retr..

[12]  Nuria Oliver,et al.  I Like It... I Like It Not: Evaluating User Ratings Noise in Recommender Systems , 2009, UMAP.

[13]  Yiming Yang,et al.  The Enron Corpus: A New Dataset for Email Classi(cid:12)cation Research , 2004 .

[14]  Changsheng Xu,et al.  Mining Cross-network Association for YouTube Video Promotion , 2014, ACM Multimedia.

[15]  B. Hogan.  The Presentation of Self in the Age of Social Media: Distinguishing Performances and Exhibitions Online , 2010 .

[16]  Petr Sojka,et al.  Software Framework for Topic Modelling with Large Corpora , 2010 .

[17]  P. McCullagh.  Analysis of Ordinal Categorical Data , 1985 .

[18]  Martha Larson,et al.  CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering , 2012, RecSys.

[19]  S. Iyengar,et al.  News That Matters: Television and American Opinion , 1987 .

[20]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[21]  Martha Larson,et al.  Collaborative Filtering beyond the User-Item Matrix , 2014, ACM Comput. Surv..

[22]  Manfred Hofer,et al.  Adolescents’ Development of Individual Interests: A Product of Multiple Goal Regulation? , 2010 .

[23]  Nishanth R. Sastry,et al.  Predicting Pinterest: Automating a Distributed Human Computation , 2015, WWW.

[24]  Alexander J. Smola,et al.  Maximum Margin Matrix Factorization for Collaborative Ranking , 2007 .

[25]  A. Kearns,et al.  Social Cohesion, Social Capital and the Neighbourhood , 2001 .

[26]  Deborah Estrin,et al.  Small data, where n = me , 2014, Commun. ACM.

[27]  David M. Blei,et al.  Probabilistic topic models , 2012, Commun. ACM.

[28]  Changhu Wang,et al.  Photo2Trip: generating travel routes from geo-tagged photos for trip planning , 2010, ACM Multimedia.

[29]  R. Putnam.  Bowling Alone: America's Declining Social Capital , 1995, The City Reader.

[30]  Deepak Agarwal,et al.  Regression-based latent factor models , 2009, KDD.

[31]  Angela P. Wetzel.  Internet, mail, and mixed‐mode surveys: The tailored design method , 2010 .

[32]  Scott Sanner,et al.  Social collaborative filtering for cold-start recommendations , 2014, RecSys '14.

[33]  Alexander J. Smola,et al.  Like like alike: joint friendship and interest propagation in social networks , 2011, WWW.

[34]  Nicola Henze,et al.  Interweaving Public User Profiles on the Web , 2010, UMAP.

[35]  R. Likert.  “Technique for the Measurement of Attitudes, A” , 2022, The SAGE Encyclopedia of Research Design.

[36]  Carmela Troncoso,et al.  Small Data , 2017, 2017 IEEE 33rd International Conference on Data Engineering (ICDE).

[37]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[38]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[39]  Jacob Cohen.  Statistical Power Analysis for the Behavioral Sciences , 1969, The SAGE Encyclopedia of Research Design.

[40]  Wei Chu,et al.  Information Services]: Web-based services , 2022 .

[41]  Yizhou Sun,et al.  Personalized entity recommendation: a heterogeneous information network approach , 2014, WSDM.

[42]  J. P. Morgan,et al.  Design and Analysis: A Researcher's Handbook , 2005, Technometrics.

[43]  Deborah Estrin,et al.  Beyond Classification: Latent User Interests Profiling from Visual Contents Analysis , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[44]  Jiebo Luo,et al.  Pinterest Board Recommendation for Twitter Users , 2015, ACM Multimedia.

[45]  Padhraic Smyth,et al.  Modeling General and Specific Aspects of Documents with a Probabilistic Topic Model , 2006, NIPS.

[46]  Danah Boyd,et al.  I tweet honestly, I tweet passionately: Twitter users, context collapse, and the imagined audience , 2011, New Media Soc..

[47]  Rashmi R. Sinha,et al.  The role of transparency in recommender systems , 2002, CHI Extended Abstracts.

[48]  A. Agresti.  Analysis of Ordinal Categorical Data: Agresti/Analysis , 2010 .

[49]  Guy Shani,et al.  Evaluating Recommendation Systems , 2011, Recommender Systems Handbook.

[50]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .