RECOGNIZING STRONG AND WEAK OPINION CLAUSES

Authors: Wilson, Theresa¹; Wiebe, Janyce²; Hwa, Rebecca²

Source: Computational Intelligence, Volume 22, Number 2, May 2006 , pp. 73-99(27)

Buy & download fulltext article:

Price: $48.00 plus tax (Refund Policy)

Abstract:

There has been a recent swell of interest in the automatic identification and extraction of opinions and emotions in text. In this paper, we present the first experimental results classifying the intensity of opinions and other types of subjectivity and classifying the subjectivity of deeply nested clauses. We use a wide range of features, including new syntactic features developed for opinion recognition. We vary the learning algorithm and the feature organization to explore the effect this has on the classification task. In 10-fold cross-validation experiments using support vector regression, we achieve improvements in mean-squared error over baseline ranging from 49% to 51%. Using boosting, we achieve improvements in accuracy ranging from 23% to 96%.

Keywords: opinion recognition; subjectivity

Document Type: Research article

DOI: http://dx.doi.org/10.1111/j.1467-8640.2006.00275.x

Affiliations: 1: Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA 15260 2: Department of Computer Science, University of Pittsburgh, Pittsburgh, PA 15260

Publication date: 2006-05-01