Tweet specific extractive summarization framework towards trending topic analysis

Abstract

Twitter establishes itself as a critical element to any social networking based applications serving itself as a rich information delivering platform. However, some users, especially new users, often find it difficult to understand trending topics in Twitter when confronted with overwhelming and unorganized tweets. Previously, there has been attempts to provide a short snippet to summarize a topic but, this does not scale up to user's expectation as it does not provide any analyzed summary of tweets. This work aims to develop a Tweet Specific Extractive Summarization system performing Trending Topic Analysis. This system analyzes trending topics through Topic based sentiment classification which summarizes the public views on selected trending topics and generates extractive sub summaries of topics over the time period using novel Tweet Feature Graph Model (TFGM). Tweet Specific Extraction Summarization framework differs from the traditional summarization in few aspects. First, conflicting summary generation could be avoided with sentiment classification enhanced by common and tweet specific feature extraction thereby sorting the data into separate sentiment corpus. Second, volume-based followed by topic modelled approach of detecting sub topic in the corpus help detect subtopics under the trending topic more efficiently. Finally, Summary generation is accomplished using the Tweet Feature Graph Model (TFGM) which incorporates tweet specific salient features. This model increases relevancy of tweets in content selection phase which in turn contributes to the increase in quality of the summaries generated.