ABSTRACT
The explosive growth in sharing and consumption of the video content on the web creates a unique opportunity for scientific advances in video retrieval, recommendation and discovery. In this paper, we focus on the task of video suggestion, commonly found in many online applications. The current state-of-the-art video suggestion techniques are based on the collaborative filtering analysis, and suggest videos that are likely to be co-viewed with the watched video. In this paper, we propose augmenting the collaborative filtering analysis with the topical representation of the video content to suggest related videos. We propose two novel methods for topical video representation. The first method uses information retrieval heuristics such as tf-idf, while the second method learns the optimal topical representations based on the implicit user feedback available in the online scenario. We conduct a large scale live experiment on YouTube traffic, and demonstrate that augmenting collaborative filtering with topical representations significantly improves the quality of the related video suggestions in a live setting, especially for categories with fresh and topically-rich video content such as news videos. In addition, we show that employing user feedback for learning the optimal topical video representations can increase the user engagement by more than 80% over the standard information retrieval representation, when compared to the collaborative filtering baseline.
Supplemental Material
- Give YouTube topics on search a whirl. http://youtube-global.blogspot.com/2010/11/give-youtube-topics-on-search-whirl.html.Google Scholar
- Youtube -- statistics. http://youtube.com/yt/press/statistics.html.Google Scholar
- Youtube data API - searching with Freebase topics. https://developers.google.com/youtube/v3/guides/searching_by_topic.Google Scholar
- A. Ahmed, B. Kanagal, S. Pandey, V. Josifovski, L. G. Pueyo, and J. Yuan. Latent factor models with additive and hierarchically-smoothed user preferences. In Proceedings of WSDM, pages 385--394, 2013. Google ScholarDigital Library
- B. Bai, J. Weston, D. Grangier, R. Collobert, K. Sadamasa, Y. Qi, O. Chapelle, and K. Weinberger. Supervised semantic indexing. In Proceedings of CIKM 2009, pages 187--196, 2009. Google ScholarDigital Library
- P. Bailey, N. Craswell, I. Soboroff, P. Thomas, A. P. de Vries, and E. Yilmaz. Relevance assessment: are judges exchangeable and does it matter. In Proceedings of SIGIR, pages 667--674, 2008. Google ScholarDigital Library
- S. Baluja, R. Seth, D. Sivakumar, Y. Jing, J. Yagnik, S. Kumar, D. Ravichandran, and M. Aly. Video suggestion and discovery for youtube: taking random walks through the view graph. In Proceedings of WWW, pages 895--904, 2008. Google ScholarDigital Library
- A. Z. Broder, D. Carmel, M. Herscovici, A. Soffer, and J. Zien. Efficient query evaluation using a two-level retrieval process. In Proceedings of CIKM, pages 426--434. ACM, 2003. Google ScholarDigital Library
- C. Burges, T. Shaked, E. Renshaw, A. Lazier, M. Deeds, N. Hamilton, and G. Hullender. Learning to rank using gradient descent. In Proceedings of ICML, pages 89--96, 2005. Google ScholarDigital Library
- R. Burke. Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction, 12(4):331--370, Nov. 2002. Google ScholarDigital Library
- B. Chen, J. Wang, Q. Huang, and T. Mei. Personalized video recommendation through tripartite graph propagation. In Proceedings of MM, pages 1133--1136, 2012. Google ScholarDigital Library
- M. Collins, R. E. Schapire, and Y. Singer. Logistic regression, adaboost and bregman distances. Machine Learning, 48(1--3):253--285, Sept. 2002. Google ScholarDigital Library
- J. Davidson, B. Liebald, J. Liu, P. Nandy, T. Van Vleet, U. Gargi, S. Gupta, Y. He, M. Lambert, B. Livingston, and D. Sampath. The youtube video recommendation system. In Proceedings of RecSys, RecSys '10, pages 293--296, New York, NY, USA, 2010. ACM. Google ScholarDigital Library
- M. Fontoura, V. Josifovski, J. Liu, S. Venkatesan, X. Zhu, and J. Zien. Evaluation strategies for top-k queries over memory-resident inverted indexes. Proceedings of the VLDB Endowment, 4(12):1213--1224, 2011.Google ScholarDigital Library
- A. Gunawardana and C. Meek. A unified approach to building hybrid recommender systems. In Proceedings of RecSys, pages 117--124, 2009. Google ScholarDigital Library
- J. Jeon, V. Lavrenko, and R. Manmatha. Automatic image annotation and retrieval using cross-media relevance models. In Proceedings of SIGIR, pages 119--126, 2003. Google ScholarDigital Library
- T. Joachims. Optimizing search engines using clickthrough data. In Proceedings of KDD, pages 133--142, 2002. Google ScholarDigital Library
- H. Li. Learning to rank for information retrieval and natural language processing. Synthesis Lectures on Human Language Technologies, 4(1):1--113, 2011. Google ScholarCross Ref
- C. D. Manning, P. Raghavan, and H. Schütze. Introduction to Information Retrieval. Cambridge University Press, New York, NY, USA, 2008. Google ScholarDigital Library
- P. Over, G. Awad, J. Fiscus, B. Antonishek, M. Michel, A. F. Smeaton, W. Kraaij, G. Quénot, et al. TRECVID 2012 -- an overview of the goals, tasks, data, evaluation mechanisms and metrics. In TRECVID 2012-TREC Video Retrieval Evaluation Online, 2012.Google Scholar
- F. Radlinski, M. Kurup, and T. Joachims. How does clickthrough data reflect retrieval quality? In Proceedings of CIKM, pages 43--52, 2008. Google ScholarDigital Library
- D. Read, G. Loewenstein, and S. Kalyanaraman. Mixing virtue and vice: Combining the immediacy effect and the diversification heuristic. Journal of Behavioral Decision Making, 12(4):257--273, 1999.Google ScholarCross Ref
- G. Salton and C. Buckley. Term-weighting approaches in automatic text retrieval. Information processing & management, 24(5):513--523, 1988. Google ScholarDigital Library
- G. Shani and A. Gunawardana. Evaluating recommendation systems. In Recommender systems handbook, pages 257--297. Springer, 2011.Google ScholarCross Ref
- V. Simonet. Classifying youtube channels: a practical system. In Proceedings of WOLE 2013, in Proceedings of WWWW companion, pages 1295--1304, 2013. Google ScholarDigital Library
- A. Singhal, C. Buckley, and M. Mitra. Pivoted document length normalization. In Proceedings of SIGIR, pages 21--29, 1996. Google ScholarDigital Library
- C. G. M. Snoek and M. Worring. Multimodal video indexing: A review of the state-of-the-art. Multimedia Tools and Applications, 25(1):5--35, Jan. 2005. Google ScholarDigital Library
- T. Tsikrika, C. Diou, A. P. de Vries, and A. Delopoulos. Image annotation using clickthrough data. In Proceedings of CIVR, pages 14:1--14:8, 2009. Google ScholarDigital Library
- C. Vondrick, D. Patterson, and D. Ramanan. Efficiently scaling up crowdsourced video annotation. International Journal of Computer Vision, pages 1--21. 10.1007/s11263-012-0564-1. 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
- B. Yang, T. Mei, X.-S. Hua, L. Yang, S.-Q. Yang, and M. Li. Online video recommendation based on multimodal fusion and relevance feedback. In Proceedings of CIVR 2007, CIVR '07, pages 73--80, 2007. Google ScholarDigital Library
- Y. Yue, R. Patel, and H. Roehrig. Beyond position bias: examining result attractiveness as a source of presentation bias in clickthrough data. In Proceedings of WWW, pages 1011--1018, 2010. Google ScholarDigital Library
Index Terms
- Up next: retrieval methods for large scale related video suggestion
Recommendations
Learning Personal Preference From Viewer's Operations for Browsing and Its Application to Baseball Video Retrieval and Summarization
Personalization is one of the most important mechanisms to make multimedia systems easy to use. In video applications, its embodiment is to tailor video contents for a particular viewer. For this purpose, we are now developing a system of retrieving and ...
Understanding item consumption orders for right-order next-item recommendation
Although the relevance problem in recommender systems, which typically refers to the similarity between the preference of the user and the items the system recommends, has been well studied, the issue of making recommendations in right orders has barely ...
What to read next?: making personalized book recommendations for K-12 users
RecSys '13: Proceedings of the 7th ACM conference on Recommender systemsFinding books that children/teenagers are interested in these days is a non-trivial task due to the diversity of topics covered in huge volumes of books with varied readability levels. Even though K-12 readers can turn to book recommenders to look for ...
Comments