Abstract
The massive growth of the micro-blogging service Twitter has shed the light on the challenging problem of summarizing a collection of large number of tweets. This paper attempts to extract topical keyphrases that would represent topics in tweets. Due to the informality, noise, and short length of tweets, such research is nontrivial. We tackle such challenges with extensive preprocessing approach. Followed by, introduction of new features that improve topical keyphrase extraction in Twitter. We start by proposing a novel unsupervised graph-based keyword ranking method, called NE-Rank, that considers word weights in addition to edge weights when calculating the ranking. Then we introduce a new approach of leveraging hashtags when extracting keyphrases. We have conducted a set of experiments showing the potential of both approaches with 16% to 39% improvement for NE-Rank and 20% improvement for hashtag enhanced extraction.