Feature-level sentiment analysis by using comparative domain corpora. Issue 5 (12th June 2016)

• Record Type: Journal Article
• Authors: Quan, Changqin; Ren, Fuji
• Is Part Of: Enterprise information systems. Volume 10:Issue 5(2016)
• Page Start: 505
• Page End: 522
• Publication Date: 2016-06-12
• Subjects: affective computing -- sentiment analysis -- frequency–inverse document frequency -- pointwise mutual information -- dependency parsing; Information storage and retrieval systems -- Periodicals; Management information systems -- Periodicals; Electronic commerce -- Periodicals; 658.4038011
• DOI: 10.1080/17517575.2014.985613
• Languages: English
• ISSNs: 1751-7575

Abstract

Abstract : Feature-level sentiment analysis (SA) is able to provide more fine-grained SA on certain opinion targets and has a wider range of applications on E-business. This study proposes an approach based on comparative domain corpora for feature-level SA. The proposed approach makes use of word associations for domain-specific feature extraction. First, we assign a similarity score for each candidate feature to denote its similarity extent to a domain. Then we identify domain features based on their similarity scores on different comparative domain corpora. After that, dependency grammar and a general sentiment lexicon are applied to extract and expand feature-oriented opinion words. Lastly, the semantic orientation of a domain-specific feature is determined based on the feature-oriented opinion lexicons. In evaluation, we compare the proposed method with several state-of-the-art methods (including unsupervised and semi-supervised) using a standard product review test collection. The experimental results demonstrate the effectiveness of using comparative domain corpora.