Lexicon-based Comments-oriented News Sentiment Analyzer system

• Published in: Expert systems with applications Vol. 39; no. 10; pp. 9166 - 9180
• Main Authors: Moreo, A., Romero, M., Castro, J.L., Zurita, J.M.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-08-2012
• Subjects: C (programming language); Design engineering; Expert systems; Feature mining; Focus detection; Internet; Lexicon-based; Linguistics; Modules; News; News analysis; Sentiment Analysis; Social networks; Feature mining; Focus detection; Sentiment Analysis; News analysis; Lexicon-based
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2012.02.057

► Able to deal with the tendency of many users to express their views in non-standard language. ► Detects the targets of users’ opinions in multi-domain scenarios. ► Linguistic modularized knowledge model with low-cost adaptability. ► Hierarchical lexicon specifically designed to analyze news comments.
Thanks to the technological revolution that has accompanied the Web 2.0, users are able to interact intensively on the Internet, as reflected in social networks, blogs, forums, etc. In these scenarios, users can speak freely on any relevant topic. However, the high volume of user-generated content makes a manual analysis of this discourse unviable. Consequently, automatic analysis techniques are needed to extract the opinions expressed in users’ comments, given that these opinions are an implicit barometer of unquestionable interest for a wide variety of companies, agencies, and organisms. We thus propose a lexicon-based Comments-oriented News Sentiment Analyzer (LCN-SA), which is able to deal with the following: (a) the tendency of many users to express their views in non-standard language; (b) the detection of the target of users’ opinions in a multi-domain scenario; (c) the design of a linguistic modularized knowledge model with low-cost adaptability. The system proposed consists of an automatic Focus Detection Module and a Sentiment Analysis Module capable of assessing user opinions of topics in news items. These modules use a taxonomy-lexicon specifically designed for news analysis. Experiments show that the results obtained thus far are extremely promising.