Title: Lexicon-based sentiment analysis by mapping conveyed sentiment to intended sentiment
Authors: Alexander Hogenboom; Malissa Bal; Flavius Frasincar; Daniella Bal; Uzay Kaymak; Franciska De Jong
Addresses: Econometric Institute, Erasmus University Rotterdam, P.O. Box 1738, NL-3000 DR Rotterdam, the Netherlands ' Econometric Institute, Erasmus University Rotterdam, P.O. Box 1738, NL-3000 DR Rotterdam, the Netherlands ' Econometric Institute, Erasmus University Rotterdam, P.O. Box 1738, NL-3000 DR Rotterdam, the Netherlands ' Econometric Institute, Erasmus University Rotterdam, P.O. Box 1738, NL-3000 DR Rotterdam, the Netherlands ' Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, P.O. Box 513, NL-5600 MB Eindhoven, the Netherlands ' Department of Computer Science, Universiteit Twente, P.O. Box 217, NL-7500 AE Enschede, the Netherlands
Abstract: As consumers nowadays generate increasingly more content describing their experiences with, e.g., products and brands in various languages, information systems monitoring a universal, language-independent measure of people's intended sentiment are crucial for today's businesses. In order to facilitate sentiment analysis of user-generated content, we propose to map sentiment conveyed by unstructured natural language text to universal star ratings, capturing intended sentiment. For these mappings, we consider a monotonically increasing step function, a naïve Bayes method, and a support vector machine. We demonstrate that the way in which natural language reveals intended sentiment differs across our datasets of Dutch and English texts. Additionally, the results of our experiments on modelling the relation between conveyed sentiment and intended sentiment suggest that language-specific sentiment scores can separate universal classes of intended sentiment from one another to a limited extent.
Keywords: sentiment analysis; star ratings; sentiment mappings; naive Bayes; support vector machines; SVM; web engineering; lexicon; conveyed sentiment; intended sentiment; modelling.
DOI: 10.1504/IJWET.2014.064768
International Journal of Web Engineering and Technology, 2014 Vol.9 No.2, pp.125 - 147
Published online: 30 Sep 2014 *
Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article