ABSTRACT
Users of popular services like Twitter and Facebook are often simultaneously overwhelmed with the amount of information delivered via their social connections and miss out on much content that they might have liked to see, even though it was distributed outside of their social circle. Both issues serve as difficulties to the users and drawbacks to the services.
Social media service providers can benefit from understanding user interests and how they interact with the service, potentially predicting their behaviors in the future. In this paper, we address the problem of simultaneously predicting user decisions and modeling users' interests in social media by analyzing rich information gathered from Twitter. The task differs from conventional recommender systems as the cold-start problem is ubiquitous, and rich features, including textual content, need to be considered. We build predictive models for user decisions in Twitter by proposing Co-Factorization Machines (CoFM), an extension of a state-of-the-art recommendation model, to handle multiple aspects of the dataset at the same time. Additionally, we discuss and compare ranking-based loss functions in the context of recommender systems, providing the first view of how they vary from each other and perform in real tasks. We explore an extensive set of features and conduct experiments on a real-world dataset, concluding that CoFM with ranking-based loss functions is superior to state-of-the-art methods and yields interpretable latent factors.
- D. Agarwal and B.-C. Chen. Regression-based latent factor models. In KDD, pages 19--28, 2009. Google ScholarDigital Library
- D. Agarwal and B.-C. Chen. fLDA: matrix factorization through latent dirichlet allocation. In WSDM, pages 91--100, 2010. Google ScholarDigital Library
- D. Agarwal, B.-C. Chen, and B. Long. Localized factor models for multi-context recommendation. In KDD, pages 609--617, 2011. Google ScholarDigital Library
- B. Bai, J. Weston, D. Grangier, R. Collobert, K. Sadamasa, Y. Qi, C. Cortes, and M. Mohri. Polynomial semantic indexing. In NIPS, pages 64--72, 2009.Google Scholar
- S. Balakrishnan and S. Chopra. Collaborative ranking. In WSDM, pages 143--152, 2012. Google ScholarDigital Library
- K. Chen, T. Chen, G. Zheng, O. Jin, E. Yao, and Y. Yu. Collaborative persoanlized tweet recommendation. In SIGIR, 2012. Google ScholarDigital Library
- T. Chen, Z. Zheng, Q. Lu, W. Zhang, and Y. Yu. Feature-based matrix factorization. Technical report, Apex Data & Knowledge Management Lab, Shanghai Jiao Tong University, 2011.Google Scholar
- P. Cremonesi, Y. Koren, and R. Turrin. Performance of recommender algorithms on top-n recommendation tasks. In RecSys, pages 39--46, 2010. Google ScholarDigital Library
- Y. Duan, L. Jiang, T. Qin, M. Zhou, and H.-Y. Shum. An empirical study on learning to rank of tweets. In COLING, pages 295--303, 2010. Google ScholarDigital Library
- J. Duchi, S. Shalev-Shwartz, Y. Singer, and T. Chandra. Efficient projections onto the l1-ball for learning in high dimensions. In ICML, pages 272--279, 2008. Google ScholarDigital Library
- Z. Gantner, L. Drumond, C. Freudenthaler, S. Rendle, and L. Schmidt-Thieme. Learning attribute-to-feature mappings for cold-start recommendations. In ICDM, pages 176--185, 2010. Google ScholarDigital Library
- R. Herbrich, T. Graepel, and K. Obermayer. Large margin rank boundaries for ordinal regression. In Advances in Large Margin Classifiers, pages 115--132. MIT Press, 2000.Google Scholar
- L. Hong, R. Bekkerman, J. Adler, and B. D. Davison. Learning to rank social update streams. In SIGIR, pages 651--660, 2012. Google ScholarDigital Library
- L. Hong, O. Dan, and B. D. Davison. Predicting popular messages in twitter. In WWW Companion, pages 57--58, 2011. Google ScholarDigital Library
- T. Joachims. Optimizing search engines using clickthrough data. In KDD, pages 133--142, 2002. Google ScholarDigital Library
- Y. Kim and K. Shim. Twitobi: A recommendation system for twitter using probabilistic modeling. In ICDM, pages 340 --349, 2011. Google ScholarDigital Library
- Y. Koren. Factor in the neighbors: Scalable and accurate collaborative filtering. ACM Transactions on Knowledge Discovery from Data (TKDD), 4(1):1:1--1:24, Jan. 2010. Google ScholarDigital Library
- Y. Koren and J. Sill. OrdRec: an ordinal model for predicting personalized item rating distributions. In RecSys, pages 117--124, 2011. Google ScholarDigital Library
- H. Lee, R. Raina, A. Teichman, and A. Y. Ng. Exponential family sparse coding with applications to self-taught learning. In IJCAI, pages 1113--1119, 2009. Google ScholarDigital Library
- C. Lin, Q. Mei, J. Han, Y. Jiang, and M. Danilevsky. The joint inference of topic diffusion and evolution in social communities. In ICDM, pages 378 --387, dec. 2011. Google ScholarDigital Library
- H.-K. Peng, J. Zhu, D. Piao, R. Yan, and Y. Zhang. Retweet modeling using conditional random fields. In ICDM Workshops, pages 336--343, 2011. Google ScholarDigital Library
- S. Rendle. Factorization machines with libFM. ACM TIST, 3(3):57:1--57:22, May 2012. Google ScholarDigital Library
- S. Rendle, C. Freudenthaler, Z. Gantner, and S.-T. Lars. BPR: Bayesian personalized ranking from implicit feedback. In UAI, pages 452--461, 2009. Google ScholarDigital Library
- S. Rendle and L. Schmidt-Thieme. Pairwise interaction tensor factorization for personalized tag recommendation. In WSDM, pages 81--90, 2010. Google ScholarDigital Library
- H. Shan and A. Banerjee. Generalized probabilistic matrix factorizations for collaborative filtering. In ICDM, pages 1025--1030, 2010. Google ScholarDigital Library
- N. Usunier, D. Buffoni, and P. Gallinari. Ranking with ordered weighted pairwise classification. In ICML, pages 1057--1064, 2009. Google ScholarDigital Library
- I. Uysal and W. B. Croft. User oriented tweet ranking: a filtering approach to microblogs. In CIKM, pages 2261--2264, 2011. Google ScholarDigital Library
- C. Wang and D. M. Blei. Collaborative topic modeling for recommending scientific articles. In KDD, pages 448--456, 2011. Google ScholarDigital Library
- M. Weimer, A. Karatzoglou, Q. V. Le, and A. Smola. CofiRank - maximum margin matrix factorization for collaborative ranking. In NIPS, pages 1593--1600, 2007.Google Scholar
- M. Weimer, A. Karatzoglou, and A. Smola. Adaptive collaborative filtering. In RecSys, pages 275--282, 2008. Google ScholarDigital Library
- J. Weston, S. Bengio, and N. Usunier. Large scale image annotation: learning to rank with joint word-image embeddings. Machine Learning, 81(1):21--35, Oct. 2010. Google ScholarDigital Library
- J. Weston, C. Wang, R. Weiss, and A. Berenzweig. Latent collaborative retrieval. In ICML, 2012.Google Scholar
- S.-H. Yang, B. Long, A. Smola, N. Sadagopan, Z. Zheng, and H. Zha. Like like alike: joint friendship and interest propagation in social networks. In WWW, pages 537--546, 2011. Google ScholarDigital Library
- S.-H. Yang, B. Long, A. J. Smola, H. Zha, and Z. Zheng. Collaborative competitive filtering: learning recommender using context of user choice. In SIGIR, pages 295--304, 2011. Google ScholarDigital Library
- Z. Yang, J. Guo, K. Cai, J. Tang, J. Li, L. Zhang, and Z. Su. Understanding retweeting behaviors in social networks. In CIKM, pages 1633--1636, 2010. Google ScholarDigital Library
- L. Zhang, D. Agarwal, and B.-C. Chen. Generalizing matrix factorization through flexible regression priors. In RecSys, pages 13--20, 2011. Google ScholarDigital Library
- J. Zhu and E. P. Xing. Sparse topical coding. In UAI, pages 831--838, 2011.Google ScholarDigital Library
Index Terms
- Co-factorization machines: modeling user interests and predicting individual decisions in Twitter
Recommendations
Using Explainability for Constrained Matrix Factorization
RecSys '17: Proceedings of the Eleventh ACM Conference on Recommender SystemsAccurate model-based Collaborative Filtering (CF) approaches, such as Matrix Factorization (MF), tend to be black-box machine learning models that lack interpretability and do not provide a straightforward explanation for their outputs. Yet explanations ...
A Scalable, Accurate Hybrid Recommender System
WKDD '10: Proceedings of the 2010 Third International Conference on Knowledge Discovery and Data MiningRecommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given resource. There are three main types of recommender systems: collaborative filtering, content-based filtering, and ...
Multi-linear interactive matrix factorization
A multi-linear interactive matrix factorization algorithm is introduced.The interactions between users and factors are empirically analyzed.Results show interactive factors significantly enhance recommendation performance. Recommender systems, which can ...
Comments