Realtime Ad Hoc Search in Twitter: Know-Center at TREC Microblog Track 2011

In this paper, we outline our experiments carried out at the TREC Microblog Track 2011. Our system is based on a plain text index extracted from Tweets crawled from twitter.com. This index has been used to retrieve candidate Tweets for the given topics. The resulting Tweets were post-processed and then analyzed using three different approaches: (i) a burst detection approach, (ii) a hashtag analysis, and (iii) a Retweet analysis. Our experiments consisted of four runs: Firstly, a combination of the Lucene ranking with the burst detection, and secondly, a combination of the Lucene ranking, the burst detection, and the hashtag analysis. Thirdly, a combination of the Lucene ranking, the burst detection, the hashtag analysis, and the Retweet analysis, and fourthly, again a combination of the Lucene ranking with the burst detection but in this case with more sophisticated query language and post-processing. We achieved the best MAP values overall in the fourth run.