NE-Rank: A Novel Graph-Based Keyphrase Extraction in Twitter
Authors:
- 1 December 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 372-379
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 key phrases 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 key phrase 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 hash tags when extracting key phrases. 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 hash tag enhanced extraction.Keywords
This publication has 13 references indexed in Scilit:
- Topic sentiment analysis in twitter2011
- Transferring topical knowledge from auxiliary long texts for short text clustering2011
- Comparing Twitter Summarization Algorithms for Multiple Post Summaries2011
- Smoothing techniques for adaptive online language models2011
- TwitterRank2010
- Thesaurus based automatic keyphrase indexing2006
- Retrieval evaluation with incomplete information2004
- Improved automatic keyword extraction given more linguistic knowledge2003
- 10.1162/jmlr.2003.3.4-5.993Applied Physics Letters, 2000
- The anatomy of a large-scale hypertextual Web search engineComputer Networks and ISDN Systems, 1998