Multimedia Semantics: Interactions Between Content and Community

Hari Sundaram, Lexing Xie, Munmun De Choudhury, Yu-Ru Lin, Apostol Natsev
2012 Proceedings of the IEEE  
This paper reviews the state of the art and some emerging issues in research areas related to pattern analysis and monitoring of web-based social communities. This research area is important for several reasons. The presence of near ubiquitous low-cost computing and communication technologies have enabled people to access and share information at unprecedented scale, which necessitates new research for making sense of such content. Furthermore, popular websites with sophisticated media sharing
more » ... nd notification features allow users to stay in touch with friends and loved ones, and also to help form explicit and implicit groups. These social structures are an important source of information for better organizing and managing multimedia. In this article, we study how media-rich social networks provide additional insight into familiar multimedia research problems, including tagging and video ranking. In particular, we advance the idea that the contextual and social aspects of media semantics are as important for successful multimedia applications as the media content itself. We examine the inter-relationship between content and social context through the prism of three key questions. First, how do we extract context in which social interactions occur? Second, does social interaction provide value to the media object? And Finally, how does social media facilitate the repurposing of shared content, and engender cultural memes? We present three case studies to examine these questions in detail. In the first case study, we show how to discover structure latent in the data, and use the structure to organize Flickr photo streams. In the second case study, we discuss how to determine the interestingness of conversationsand of participants-around videos uploaded to YouTube. Finally, we show how analysis of visual content-tracing content remixes, in particular-can help us understand the relationship amongst YouTube participants. For each case, we present an overview of recent work and review the state of the art. We also discuss two emerging issues related to the analysis of social networks-robust data sampling and scalable data analysis.
doi:10.1109/jproc.2012.2191529 fatcat:tayhtgkr6jfz7l2efpic4ygaqy