Streaming First Story Detection with application to Twitter

摘要: With the recent rise in popularity and size of social media, there is a growing need for systems that can extract useful information from this amount data. We address problem detecting new events stream Twitter posts. To make event detection feasible on web-scale corpora, we present an algorithm based locality-sensitive hashing which able overcome limitations traditional approaches, while maintaining competitive results. In particular, comparison with state-of-the-art system first story task shows achieve over order magnitude speedup processing time, retaining comparable performance. Event experiments collection 160 million posts show celebrity deaths are fastest spreading news Twitter.