Using an Emotion-based Model and Sentiment Analysis Techniques to Classify Polarity for Reputation.
Jorge Carrillo‐de‐Albornoz, Irina Chugur, Enrique Amigó · 2012
Abstract. Online Reputation Management is a novel and active area in Computational Linguistics. Closely related to opinion mining and senti-ment analysis, it incorporates new features to traditional tasks like po-larity detection. In this paper, we study the feasibility of applying com-plex sentiment analysis methods to classifying polarity for reputation. We adapt an existing emotional concept-based system for sentiment analysis to determine polarity of tweets with reputational information about com-panies. The original system has been extended to work with texts in En-glish and in Spanish, and to include a module for filtering tweets accord-ing to their relevance to each company. The resulting UNED system for profiling task participated in the first RepLab campaign. The experimental results prove that sentiment analysis techniques are a good starting point for creating systems for automatic detection of polarity for reputation.