Abstract
Topic detection on web videos can effectively help collecting users’ feedback and emotional tendency. With the features of relatively short, topic alignment and time synchronization, Danmaku comments can significantly extend the applications of topic detection. However, most of the current topic detection approaches fall short of considering the interior relation between adjacent time-steps which ignores the underlying temporal effects. To address this problem, we introduce a Joint Online Nonnegative Matrix Factorization model (JO-NMF) to detect latent topics with automatically exploiting Danmaku comments. Experimental results show great advantages of our proposed model on real-world Danmaku datasets. The results show our model outperforms baselines in topic detection with perplexity and RMSE for the noisy temporal data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cao, J., Zhang, Y., Ji, R., Xei, F., Su, Y.: Web video topics discovery and structuralization with social network. Neurocomputing 172(C), 53–63 (2016)
Hayashi, K., Maehara, T., Toyoda, M., Kawarabayashi, K.I.: Real-time top-R topic detection on twitter with topic hijack filtering. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 417–426. ACM (2015)
He, M., Ge, Y., Chen, E., Liu, Q., Wang, X.: Exploring the emerging type of comment for online videos: Danmu. ACM Trans. Web 12(1), 1 (2017)
Kalyanam, J., Mantrach, A., Saez-Trumper, D., Vahabi, H., Lanckriet, G.: Leveraging social context for modeling topic evolution. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 517–526 (2015)
Li, J., Liao, Z., Zhang, C., Wang, J.: Event detection on online videos using crowdsourced time-sync comment. In: International Conference on Cloud Computing and Big Data (2017)
Lv, G., Xu, T., Chen, E., Liu, Q., Zheng, Y.: Reading the videos: temporal labeling for crowdsourced time-sync videos based on semantic embedding. In: AAAI, pp. 3000–3006 (2016)
Ma, X., Cao, N.: Video-based evanescent, anonymous, asynchronous social interaction: motivation and adaption to medium. In: ACM Conference on Computer Supported Cooperative Work and Social Computing, pp. 770–782 (2017)
Vaca, C.K., Mantrach, A., Jaimes, A., Saerens, M.: A time-based collective factorization for topic discovery and monitoring in news. In: International Conference on World Wide Web, pp. 527–538 (2014)
Wu, B., Zhong, E., Tan, B., Horner, A., Yang, Q.: Crowdsourced time-sync video tagging using temporal and personalized topic modeling. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 721–730 (2014)
Yao, Y., Bort, J., Huang, Y.: Understanding Danmaku’s potential in online video learning. In: CHI Conference Extended Abstracts on Human Factors in Computing Systems, pp. 3034–3040 (2017)
Yu, H.F., Rao, N., Dhillon, I.S.: Temporal regularized matrix factorization for high-dimensional time series prediction. In: Advances in Neural Information Processing Systems, pp. 847–855 (2016)
Acknowledgments
This research is funded by the Science and Technology Commission of Shanghai Municipality (No. 16511102702).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Bai, Q., Hu, Q., Fang, F., He, L. (2018). Topic Detection with Danmaku: A Time-Sync Joint NMF Approach. In: Hartmann, S., Ma, H., Hameurlain, A., Pernul, G., Wagner, R. (eds) Database and Expert Systems Applications. DEXA 2018. Lecture Notes in Computer Science(), vol 11030. Springer, Cham. https://doi.org/10.1007/978-3-319-98812-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-319-98812-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98811-5
Online ISBN: 978-3-319-98812-2
eBook Packages: Computer ScienceComputer Science (R0)