Current Events: Twitter - gt-big-data/wiki GitHub Wiki

Question

Can we cluster tweets to find current events? Are some accounts more responsible for starting these clusters of tweets on a recent event? How do the clusters on recent events spread (virality)? Measure importance/relevance of information through virality?

Examples would be how does "The princess had a baby?" spread.

People

Name: Saman Shareghi, Utkarsh Garg, Philippe Laban, Patrick Violette

Info

Some information about clustering analysis in the context of short messages: http://stackoverflow.com/questions/19054062/doubts-about-clustering-methods-for-tweets

github with sample code for streaming from twitter: https://github.com/gt-big-data/twitter-api-sentiment-analysis

twitter streaming api (filter): https://dev.twitter.com/docs/api/1.1/post/statuses/filter

python natural language toolkit: http://nltk.org/