ABSTRACT
We propose visual memes, or frequently reposted short video segments, for tracking large-scale video remix in social media. Visual memes are extracted by novel and highly scalable detection algorithms that we develop, with over 96% precision and 80% recall. We monitor real-world events on YouTube, and we model interactions using a graph model over memes, with people and content as nodes, and meme postings as links. This allows us to define several measures of influence. These abstractions, using more than two million video shots from several large-scale event datasets, enable us to quantify and efficiently extract several important observations: over half of the videos contain re-mixed content, which appears rapidly; video view counts, particularly high ones, are poorly correlated with the virality of content; the influence of traditional news media versus citizen journalists varies from event to event; iconic single images of an event are easily extracted; and content that will have long lifespan can be predicted within a day after it first appears. Visual memes can be applied to a number of social media scenarios: brand monitoring, social buzz tracking, ranking content and users, among others.
- What is the Klout score? Understanding the influence metric. http://klout.com/kscore, retrieved April 2011.Google Scholar
- Thanks, YouTube community, for two BIG gifts on our sixth birthday!, May 2011. The official YouTube blog, http://youtube-global.blogspot.com/2011/05/thanks-youtube-community-for-two-big.html.Google Scholar
- F. Benevenuto, T. Rodrigues, V. Almeida, J. Almeida, and K. Ross. Video interactions in online video social networks. ACM Trans. on Multimedia Computing, Communications, and Applications (TOMCCAP), 5(4):30, 2009. Google ScholarDigital Library
- J.-I. Biel and D. Gatica-Perez. Voices of vlogging. In AAAI Int. Conf. on Weblogs and Social Media (ICWSM), 5 2010.Google Scholar
- M. Cha, H. Haddadi, F. Benevenuto, and K. Gummadi. Measuring user influence in twitter: The million follower fallacy. In 4th Intl. Conf. on Weblogs and Social Media (ICWSM), 2010.Google Scholar
- M. Cha, H. Kwak, P. Rodriguez, Y.-Y. Ahn, and S. Moon. I tube, you tube, everybody tubes: Analyzing the world's largest user generated content video system. In Proc. ACM IMC, pages 1--14, 2007. Google ScholarDigital Library
- C.-C. Chang and C.-J. Lin. LIBSVM: A library for support vector machines, 2001. \surlhttp://www.csie.ntu.edu.tw/ cjlin/libsvm.Google Scholar
- M. Cherubini, R. de Oliveira, and N. Oliver. Understanding near-duplicate videos: A user-centric approach. In Proc. ACM Intl. Conf. on Multimedia, pages 35--44, 2009. Google ScholarDigital Library
- R. Crane and D. Sornette. Viral, quality, and junk videos on YouTube: Separating content from noise in an information-rich environment. In Proc. of AAAI symposium on Social Information Processing, Menlo Park, CA, 2008.Google Scholar
- M. De Choudhury, H. Sundaram, A. John, and D. D. Seligmann. What makes conversations interesting?: Themes, participants and consequences of conversations in online social media. In WWW, pages 331--340, 2009. Google ScholarDigital Library
- T. Fawcett. ROC graphs: Notes and practical considerations for researchers. Machine Learning, 31:1--38, 2004.Google Scholar
- B. A. Galler and M. J. Fisher. An improved equivalence algorithm. Communications of ACM, 7(5):301--303, 1964. Google ScholarDigital Library
- C. Gini. Measurement of inequality of ncomes. Economic Journal, 31:124--126, 1921.Google ScholarCross Ref
- M. Gladwell. The tipping point: How little things can make a big difference. Little, Brown and Co., 2000.Google Scholar
- R. Hong, J. Tang, H.-K. Tan, S. Yan, C.-W. Ngo, and T.-S. Chua. Beyond search: Event driven summarization for web videos. ACM Trans. on Multimedia Computing, Communications, and Applications (TOMCCAP), 2011. Google ScholarDigital Library
- J. Huang, S. Kumar, M. Mitra, W. Zhu, and R. Zabih. Spatial color indexing and applications. International Journal of Computer Vision, 35(3), December 1999. Google ScholarDigital Library
- L. Kennedy and S.-F. Chang. Internet image archaeology: Automatically tracing the manipulation history of photographs on the web. In Proc. ACM Multimedia, 2008. Google ScholarDigital Library
- H. Kwak, C. Lee, H. Park, , and S. Moon. What is Twitter, a Social Network or a News Media? . In Proc. WWW, 2010. Google ScholarDigital Library
- J. Leskovec, L. Backstrom, and J. Kleinberg. Meme-tracking and the dynamics of the news cycle. In Proc. KDD, 2009. Google ScholarDigital Library
- T. Liu, C. Rosenberg, and H. A. Rowley. Clustering billions of images with large scale nearest neighbor search. In IEEE Workshop on Applications of Computer Vision, 2007. Google ScholarDigital Library
- M. Muja and D. G. Lowe. Fast approximate nearest neighbors with automatic algorithm configuration. In Intl. Conf. on Computer Vision Theory and Applications, 2009.Google Scholar
- A. Natsev, M. Hill, and J. Smith. Design and evaluation of an effective and efficient video copy detection system. In IEEE Intl. Conf. on Multimedia and Expo (ICME), 2010.Google ScholarCross Ref
- P. Schmitz, P. Shafton, R. Shaw, S. Tripodi, B. Williams, and J. Yang. International remix: Video editing for the web. In Proc. ACM Multimedia, page 798. ACM, 2006. Google ScholarDigital Library
- P. Snickars and P. Vonderau. The YouTube Reader. National Library of Sweden, 2010.Google Scholar
- G. Szabo and B. A. Huberman. Predicting the popularity of online content. Commun. ACM, 53:80--88, August 2010. Google ScholarDigital Library
- H.-K. Tan, X. Wu, C.-W. Ngo, and W.-L. Zhao. Accelerating near-duplicate video matching by combining visual similarity and alignment distortion. In Proc. ACM Multimedia, page 861, 2008. Google ScholarDigital Library
- J. Wang, S. Kumar, and S.-F. Chang. Semi-supervised hashing for scalable image retrieval. In IEEE CVPR, San Francisco, USA, June 2010.Google ScholarCross Ref
Index Terms
- Visual memes in social media: tracking real-world news in YouTube videos
Recommendations
On the Origins of Memes by Means of Fringe Web Communities
IMC '18: Proceedings of the Internet Measurement Conference 2018Internet memes are increasingly used to sway and manipulate public opinion. This prompts the need to study their propagation, evolution, and influence across the Web. In this paper, we detect and measure the propagation of memes across multiple Web ...
The diffusion of political memes in social media: keynote abstract
PLEAD '12: Proceedings of the first edition workshop on Politics, elections and dataThis talk presents ongoing work on the study of information diffusion in social media, focusing in particular on political communication in the Twitter microblogging network. Social media platforms play an important role in shaping political discourse ...
Catching a viral video
The sharing and re-sharing of videos on social sites, blogs e-mail, and other means has given rise to the phenomenon of viral videos--videos that become popular through internet sharing. In this paper we seek to better understand viral videos on YouTube ...
Comments