Predicting User Engagement in Twitter with Collaborative Ranking

Collaborative Filtering (CF) is a core component of popular web-based services such as Amazon, YouTube, Netflix, and Twitter. Most applications use CF to recommend a small set of items to the user. For instance, YouTube presents to a user a list of top-n videos she would likely watch next based on her rating and viewing history. Current methods of CF evaluation have been focused on assessing the quality of a predicted rating or the ranking performance for top-n recommended items. However, restricting the recommender system evaluation to these two aspects is rather limiting and neglects other dimensions that could better characterize a well-perceived recommendation. In this paper, instead of optimizing rating or top-n recommendation, we focus on the task of predicting which items generate the highest user engagement. In particular, we use Twitter as our testbed and cast the problem as a Collaborative Ranking task where the rich features extracted from the metadata of the tweets help to complement the transaction information limited to user ids, item ids, ratings and timestamps. We learn a scoring function that directly optimizes the user engagement in terms of nDCG@10 on the predicted ranking. Experiments conducted on an extended version of the MovieTweetings dataset, released as part of the RecSys Challenge 2014, show the effectiveness of our approach.

[1]  Suhrid Balakrishnan,et al.  Collaborative ranking , 2012, WSDM '12.

[2]  Matthew Michelson,et al.  Tweet Disambiguate Entities Retrieve Folksonomy SubTree Step 1 : Discover Categories Generate Topic Profile from SubTrees Step 2 : Discover Profile Topic Profile : “ English Football ” “ World Cup ” , 2011 .

[3]  Steffen Rendle,et al.  Factorization Machines with libFM , 2012, TIST.

[4]  Qiang Wu,et al.  Learning to Rank Using an Ensemble of Lambda-Gradient Models , 2010, Yahoo! Learning to Rank Challenge.

[5]  Yi Chang,et al.  Yahoo! Learning to Rank Challenge Overview , 2010, Yahoo! Learning to Rank Challenge.

[6]  Toon De Pessemier,et al.  MovieTweetings: a movie rating dataset collected from twitter , 2013, RecSys 2013.

[7]  Lars Schmidt-Thieme,et al.  Real-time top-n recommendation in social streams , 2012, RecSys.

[8]  Christopher J. C. Burges,et al.  From RankNet to LambdaRank to LambdaMART: An Overview , 2010 .

[9]  Gediminas Adomavicius,et al.  Context-aware recommender systems , 2008, RecSys '08.

[10]  Maksims Volkovs,et al.  Collaborative Ranking With 17 Parameters , 2012, NIPS.

[11]  Simon Dooms,et al.  Recommender systems challenge 2014 , 2014, RecSys '14.

[12]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[13]  Tie-Yan Liu,et al.  Learning to rank for information retrieval , 2009, SIGIR.

[14]  Avare Stewart,et al.  Epidemic Intelligence for the Crowd, by the Crowd , 2012, ICWSM.

[15]  Proceedings of the Yahoo! Learning to Rank Challenge, held at ICML 2010, Haifa, Israel, June 25, 2010 , 2011, Yahoo! Learning to Rank Challenge.

[16]  Katrien Verbert,et al.  Recommender systems challenge 2012 , 2012, RecSys '12.

[17]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

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

[19]  Mihai Georgescu,et al.  Swarming to rank for recommender systems , 2012, RecSys.

[20]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[21]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[22]  J. Friedman.  Stochastic gradient boosting , 2002 .

[23]  Nicola Henze,et al.  Analyzing the Blogosphere for Predicting the Success of Music and Movie Products , 2010, 2010 International Conference on Advances in Social Networks Analysis and Mining.

[24]  Tie-Yan Liu,et al.  Learning to Rank for Information Retrieval , 2011 .

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