doi: 10.4304/jsw.9.2.274-279
Feature-based Sentiment Analysis Approach for Product Reviews
- 1 College of Information Engineering, Capital Normal University, Beijing, China
- 2 Grasslands Research Centre, New Zealand
Abstract
The researches and applications of sentimentanalysis become increasingly important with the rapidgrowth of online reviews. But traditional sentiment analysismodels have been lacking in concern on the modifyingrelationship between words for sentiment analysis ofChinese reviews, and limit the development of opinionmining. This paper proposes a feature-based vector modeland a novel weighting algorithm for sentiment analysis ofChinese product reviews. It considers both modifyingrelationships between words and punctuations in reviewtexts. Specifically, it can classify reviews into two categories,i.e., positive and negative, and can also represent thesentiment strength by adverb of degree. Moreover, a novelfeature extraction method based on dependency parsing ispresented to identify the corresponding aspects thatopinions words modify. We conduct some experiments toevaluate our algorithms, and demonstrate that the proposedapproaches are efficient and promising.
Keywords
- sentiment analysis
- dependency parsing
- p
How to Cite
Hanshi Wang, Lizhen Liu, Wei Song, and Jingli Lu, "Feature-based Sentiment Analysis Approach for Product Reviews," Journal of Software, vol. 9, no. 2, pp. 274-279, 2014. https://doi.org/ 10.4304/jsw.9.2.274-279
Copyright & License
Copyright © 2014 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).