Xuhong Gu
ABSTRACT
The online video streaming service is of huge market values with billions of worldwide users. For online video providers, e.g., Netflix, Youku, the crucial question is how to understand users' view behaviors and preferences because this knowledge is important for their business operation. Existing solutions mainly rely on analyzing users' historical view records, which however are not always available, especially for new videos and unprovided videos. Different from existing solutions, we propose to infer user behaviors and preferences by jointly analyzing data collected from multiple platforms (e.g., video streaming systems, video databases, etc.). In particular, we use the movie data crawled from a leading video streaming system (i.e., Youku), and a well-known video database in China (i.e., Douban) for this study. Our investigation points out that movie quality (evaluated in terms of Douban scores) and release date jointly influence viewers' preferences. In addition, we reveal a series of user behaviors, e.g., users are reluctant to post comments or ratings for movies they do not like, and user eyeballs are heavily captured by new movies. Understanding of these user behaviors covered by this study is essential for video recommendation and video popularity prediction which can benefit video procurement and advertisement campaign.
- Douban. https://www.douban.com/.Google Scholar
- IMDB. http://www.imdb.com/.Google Scholar
- Youku. http://www.youku.com/.Google Scholar
- A Ali-Eldin, M Kihl, J Tordsson, and E Elmroth. 2015. Analysis and characterization of a video-on-demand service workload. In Proceedings of the 6th ACM MMSys. ACM, 189--200. Google ScholarDigital Library
- Min Chen, Yixue Hao, Yong Li, Di Wu, and Dijiang Huang. 2015. Demo: Lives: Learning through interactive video and emotion-aware system. In Proceedings of the 16th ACM International Symposium on Mobile Ad Hoc Networking and Computing. ACM, 399--400. Google ScholarDigital Library
- Min Chen, Yixue Hao, Shiwen Mao, Di Wu, and Yuan Zhou. 2016. User Intent-oriented Video QoE with Emotion Detection Networking. IEEE Globelcom (2016), 1552--1559.Google Scholar
- X Cheng, J Liu, and C Dale. 2013. Understanding the characteristics of internet short video sharing: A YouTube-based measurement study. IEEE TMM 15, 5 (June 2013), 1184--1194. Google ScholarDigital Library
- L Cui, L Dong, X Fu, Z Wen, N Lu, and G Zhang. 2016. A video recommendation algorithm based on the combination of video content and social network. Concurrency and Computation: Practice and Experience (June 2016).Google Scholar
- Z Deng, J Sang, and C Xu. 2013. Personalized video recommendation based on cross-platform user modeling. In Proceedings of the IEEE ICME. IEEE, 1--6.Google Scholar
- F Figueiredo. 2013. On the prediction of popularity of trends and hits for user generated videos. In Proceedings of the 6th ACM WSDM. ACM, 741--746. Google ScholarDigital Library
- T Han, H Yao, C Xu, X Sun, Y Zhang, and J Corso. 2016. Dancelets Mining for Video Recommendation Based on Dance Styles. IEEE TMM PP, 99 (November 2016), 1--13. Google ScholarDigital Library
- Y Koren. 2010. Collaborative filtering with temporal dynamics. ACM CACM 53, 4(2010), 89--97. Google ScholarDigital Library
- SS Krishnan and RK Sitaraman. 2013. Understanding the effectiveness of video ads: a measurement study. In ACM/USENIX IMC. ACM, 149--162. Google ScholarDigital Library
- SS Krishnan and RK Sitaraman. 2013. Video stream quality impacts viewer behavior: inferring causality using quasi-experimental designs. IEEE/ACM ToN 21, 6 (September 2013), 2001--2014. Google ScholarDigital Library
- Zhi L, Y Ji, X Jiang, and Y Tanaka. 2016. User-behavior Driven Video Caching in Content Centric Network. In Proceedings of the 3rd ACM ICN. ACM, 197--198. Google ScholarDigital Library
- H Li, X Ma, F Wang, J Liu, and K Xu. 2013. On popularity prediction of videos shared in online social networks. In Proceedings of the 22nd ACM CIKM. ACM, 169--178. Google ScholarDigital Library
- NN Liu, Min Zhao, E Xiang, and Q Yang. 2010. Online evolutionary collaborative filtering. In Proceedings of the 4th ACM RecSys. ACM, 95--102. Google ScholarDigital Library
- S Sikdar, A Chaudhary, S Kumar, N Ganguly, A Chakraborty, G Kumar, A Patil, and A Mukherjee. 2016. Identifying and Characterizing Sleeping Beauties on YouTube. In Proceedings of the 19th ACM CSCW. ACM, 405--408. Google ScholarDigital Library
- J Wu, Y Zhou, DM Chiu, and Z Zhu. 2015. Modeling dynamics of online video popularity. In Proceedings of the 23rd IEEE/ACM IWQoS. IEEE, 141--146.Google ScholarCross Ref
- Y Xu, Z Xiao, H Feng, T Yang, B Hu, and Y Zhou. 2016. Modeling Buffer Starvations of Video Streaming in Cellular Networks with Large-Scale Measurement of User Behavior. IEEE PMC PP, 99 (October 2016), 1--15.Google Scholar
- H Yu, L Xie, and S Sanner. 2014. Twitter-driven youtube views: Beyond individual influencers. In Proceedings of the 22nd ACM MM. ACM, 869--872. Google ScholarDigital Library
- C Zhang and J Liu. 2015. On crowdsourced interactive live streaming: a Twitch. tv-based measurement study. In Proceedings of the 25th ACM NOSSDAV. ACM, 55--60. Google ScholarDigital Library
- P Zhou, Y Zhou, D Wu, and H Jin. 2016. Differentially Private Online Learning for Cloud-Based Video Recommendation with Multimedia Big Data in Social Networks. IEEE TMM 18, 6 (March 2016), 1217--1229.Google Scholar
Index Terms
- Unveiling Latent Behaviors of Video Viewers with Cross-Platform Information
Recommendations
User feedback and preferences mining
UMAP'12: Proceedings of the 20th international conference on User Modeling, Adaptation, and PersonalizationIn this paper, we present our vision and some initial experiments on how to anticipate significance, similarity or polarity of various types of (preferably implicit) user feedback and how to form individual user preference for recommendation. Throughout ...
A New Approach for Recommender System
ICACS '17: Proceedings of the 1st International Conference on Algorithms, Computing and SystemsIn today's e-commerce environment, Collaborative Filtering (CF) is a widely used algorithm for recommender system, which is to identify the users who have similar preferences to the target user, and to predict the preference of the target user according ...
Preference-based user rating correction process for interactive recommendation systems
In most of the recommendation systems, user rating is an important user activity that reflects their opinions. Once the users return their ratings about items the systems have suggested, the user ratings can be used to adjust the recommendation ...
Comments