Probabilistic latent semantic indexing
Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
The Journal of Machine Learning Research
Comparing twitter and traditional media using topic models
ECIR'11 Proceedings of the 33rd European conference on Advances in information retrieval
Characterizing the life cycle of online news stories using social media reactions
Proceedings of the 17th ACM conference on Computer supported cooperative work & social computing
| Hi-index | 0.00 |
In this work, we analyze the responses of users to public events through social media. We apply analytical methods on transcripts from public speeches and tweets from Twitter users to provide a deeper understanding of the feedback of individuals on events through Twitter. In particular, we develop a joint statistical model of the messages posted by Twitter users and the paragraphs from speeches, based on their topical connections. Our analysis of President Obama's speech on the Middle East on May 19, 2011 and a sample of 800 tweets contributed during the speech shows that the majority of users on Twitter do not directly comment on a specific paragraph of a speech. On the contrary, their feedback is high level and related to the general topics of the event. In addition, the tweets that directly comment on a specific paragraph in the speech are related to topics of high interest in the Middle East.