A Computational Approach to Finding Contradictions in User Opinionated Text

The rapid growth of Web 2.0 and wide popularity of social media have brought the challenge of digesting and understanding large amounts of user-generated text. Automatically finding contradictions from user opinionated text is a potential solution to help sense-making and decision-making process from those user opinions. However, the problem of contradiction detection is understudied in social media analysis field. This study presents a computational approach to detecting contradictions in user opinionated text. Specifically, a typology of contradictions was proposed, and then the state-of-art deep learning models were adopted and enhanced by three methods of incorporating sentiment analysis. The enhanced models were evaluated with Amazon's customer reviews. The best model was selected and applied to a collection of tweets from Twitter to demonstrate its usefulness in understanding contradiction semantically and quantitatively in a large amount of user opinionated text.