Student Research

Generation of Micro-opinion from Conversational Texts

With the advancement of internet technology, there has been proliferation of conversational texts in the form of blog posts, comments, reviews and so on. It has become daunting task for users to extract very concise and meaningful opinions of people from such conversational texts. Traditional summarization approaches alone can not use to handle this task. It needs to be incorporated with sentiment analysis (or opinion mining which refers to the use of natural language processing, text analysis and computational linguistics to identify and extract subjective information in source materials). In this work, we thus integrate both summarization and sentiment analysis to generate micro-opinions (short summaries) of these conversational texts and identify different challenges in this domain.


In Collection: