ABSTRACT
These days, several hours of new video content is uploaded to the internet every second. It is simply impossible for anyone to see every piece of video which could be engaging or even useful to them. Therefore it is desirable to identify videos that might be regarded as engaging automatically, for a variety of applications such as recommendation and personalized video segmentation etc. This paper explores how multimodal characteristics of video, such as prosodic, visual and paralinguistic features, can help in assessing user engagement with videos. The approach proposed in this paper achieved good accuracy (maximum F score of 96.93 %) through a novel combination of features extracted directly from video recordings, demonstrating the potential of this method in identifying engaging content.
- A. Anwar, G. I. Salama, and M. B. Abdelhalim. Video Classification And Retrieval Using Arabic Closed Caption. In ICIT 2013 The 6th International Conference on Information Technology VIDEO, 2013.Google Scholar
- S. Attfield, B. Piwowarski, and G. Kazai. Towards a science of user engagement ( Position Paper ). In WSDM Workshop on User Modelling for Web Applications, Hong Kong, 2011.Google Scholar
- F. Bellard, M. Niedermayer, et al. Ffmpeg. ht tp://ffmpeg. org, 2012.Google Scholar
- S. Benini, P. Migliorati, and R. Leonardi. Statistical Skimming of Feature Films. International Journal of Digital Multimedia Broadcasting, 2010:1--11, 2010.Google ScholarCross Ref
- G. Bradski. The OpenCV Library. Dr. Dobb's Journal of Software Tools, 2000.Google Scholar
- D. Brezeale and D. J. Cook. Learning video preferences using visual features and closed captions. IEEE Multimedia, 16(3):39--47, 2009. Google ScholarDigital Library
- F. Chen, C. De Vleeschouwer, and A. Cavallaro. Resource allocation for personalized video summarization. IEEE Transactions on Multimedia, 16(2):455--469, 2014. Google ScholarDigital Library
- F. Dobrian, A. Awan, D. Joseph, A. Ganjam, J. Zhan, V. Sel, I. Stoica, and H. Zhang. Understanding the Impact of Video Quality on User Engagement. In Communications of the ACM, pages 91--99, 2013. Google ScholarDigital Library
- A. Dong and H. Li. ONTOLOGY-DRIVEN ANNOTATION AND ACCESS OF PRESENTATION VIDEO DATA. Estudios de Economá Aplicada, 2008.Google Scholar
- G. Evangelopoulos, A. Zlatintsi, A. Potamianos, P. Maragos, K. Rapantzikos, G. Skoumas, and Y. Avrithis. Multimodal saliency and fusion for movie summarization based on aural, visual, and textual attention. IEEE Transactions on Multimedia, 15(7):1553--1568, 2013. Google ScholarDigital Library
- F. Eyben, F. Weninger, F. Groß, and B. Schuller. Recent developments in opensmile, the munich open-source multimedia feature extractor. In Proceedings of the 21st ACM international conference on Multimedia, pages 835--838. ACM, 2013. Google ScholarDigital Library
- P. J. Guo, J. Kim, and R. Rubin. How Video Production Affects Student Engagement : An Empirical Study of MOOC Videos. In L@S 2014 Proceedings of the 1st ACM Conference on Learning at Scale, pages 41--50, 2014. Google ScholarDigital Library
- M. Haesen, J. Meskens, K. Luyten, K. Coninx, J. H. Becker, T. Tuytelaars, G.-J. Poulisse, P. T. Pham, and M.-F. Moens. Finding a needle in a haystack: an interactive video archive explorer for professional video searchers. Multimedia Tools and Applications, 63(2):331--356, May 2011. Google ScholarDigital Library
- R. Lienhart, A. Kuranov, and V. Pisarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection. In Proceedings of the 25th DAGM Pattern Recognition Symposium, pages 297--304, 2003.Google ScholarCross Ref
- H. L. O'Brien and E. G. Toms. Examining the generalizability of the User Engagement Scale (UES) in exploratory search. Information Processing and Management, 49(5):1092--1107, 2013. Google ScholarDigital Library
- F. A. Salim. From artifact to content source: Using multimodality in video to support personalized recomposition. In User Modeling, Adaptation and Personalization 2015. UMAP, 2015.Google Scholar
- B. Schuller, S. Steidl, A. Batliner, A. Vinciarelli, K. Scherer, F. Ringeval, M. Chetouani, F. Weninger, F. Eyben, E. Marchi, et al. The interspeech 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. 2013.Google Scholar
- S. Tan, J. Bu, X. Qin, C. Chen, and D. Cai. Cross domain recommendation based on multi-type media fusion. Neurocomputing, 127:124--134, Mar. 2014. Google ScholarDigital Library
- S. Wernicke. Lies, damned lies and statistics (about tedtalks). http://go.ted.com/bDrm, 2010.Google Scholar
Index Terms
- Analyzing Multimodality of Video for User Engagement Assessment
Recommendations
User Engagement with Chatbots: A Discursive Psychology Approach
CUI '20: Proceedings of the 2nd Conference on Conversational User InterfacesConversational agents have transcended into multiple industries with increased ability for user engagement in intelligent conversation. Conversations with chatbots are different from interpersonal communication in terms of turn-taking, intentions, and ...
Effects of Personalized and Aggregate Top-N Recommendation Lists on User Preference Ratings
Prior research has shown a robust effect of personalized product recommendations on user preference judgments for items. Specifically, the display of system-predicted preference ratings as item recommendations has been shown in multiple studies to bias ...
Generating semantically enriched user profiles for Web personalization
Traditional collaborative filtering generates recommendations for the active user based solely on ratings of items by other users. However, most businesses today have item ontologies that provide a useful source of content descriptors that can be used ...
Comments