Referral Web: combining social networks and collaborative filtering
Communications of the ACM
A survey on the use of relevance feedback for information access systems
The Knowledge Engineering Review
I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system
Proceedings of the 7th ACM SIGCOMM conference on Internet measurement
Youtube traffic characterization: a view from the edge
Proceedings of the 7th ACM SIGCOMM conference on Internet measurement
Why we twitter: understanding microblogging usage and communities
Proceedings of the 9th WebKDD and 1st SNA-KDD 2007 workshop on Web mining and social network analysis
Video suggestion and discovery for youtube: taking random walks through the view graph
Proceedings of the 17th international conference on World Wide Web
Analyzing the video popularity characteristics of large-scale user generated content systems
IEEE/ACM Transactions on Networking (TON)
Digging Digg: Comment Mining, Popularity Prediction, and Social Network Analysis
WISM '09 Proceedings of the 2009 International Conference on Web Information Systems and Mining
TwitterMonitor: trend detection over the twitter stream
Proceedings of the 2010 ACM SIGMOD International Conference on Management of data
Emerging topic detection on Twitter based on temporal and social terms evaluation
Proceedings of the Tenth International Workshop on Multimedia Data Mining
The tube over time: characterizing popularity growth of youtube videos
Proceedings of the fourth ACM international conference on Web search and data mining
| Hi-index | 0.00 |
User-generated content (UGC) systems such as Twitter, Face-book, and YouTube are quickly becoming the dominant form of information exchange on the web: shifting informational power from media conglomerates to individual users. Understanding the popularity trends in UGC content has proven problematic as traditional content popularity techniques (e.g. those developed for television) are not suited for the disparate origins and ephemeral lifecycle of UGC. Content-based trend detection with UGC systems has been an intensely growing field of research in recent years, yet surprisingly, there is no single method or approach that can be used to track and compare trends in user posts across multiple UGC sources. Therefore, in this work, we develop a standard system for detecting emerging trends in user posts for UGC that contains some form of textual data. We demonstrate the use and implementation of this system through a case study with approximately 2 million YouTube video posts. Furthermore, to help facilitate future comparative studies in UGC trend analysis, we have made this system open-source and straightforward to integrate with various UGC systems (Twitter, Facebook, Flickr, Digg, Blogger, etc.).