Welcome to the InfoSci Platform
Reference Hub2
Rule-Based Polarity Aggregation Using Rhetorical Structures for Aspect-Based Sentiment Analysis

Rule-Based Polarity Aggregation Using Rhetorical Structures for Aspect-Based Sentiment Analysis

Nuttapong Sanglerdsinlapachai, Anon Plangprasopchok, Tu Bao Ho, Ekawit Nantajeewarawat
Copyright: © 2019 |Volume: 10 |Issue: 3 |Pages: 17
ISSN: 1947-8208|EISSN: 1947-8216|EISBN13: 9781522566960|DOI: 10.4018/IJKSS.2019070104
Cite Article Cite Article

MLA

Sanglerdsinlapachai, Nuttapong, et al. "Rule-Based Polarity Aggregation Using Rhetorical Structures for Aspect-Based Sentiment Analysis." IJKSS vol.10, no.3 2019: pp.44-60. http://doi.org/10.4018/IJKSS.2019070104

APA

Sanglerdsinlapachai, N., Plangprasopchok, A., Ho, T. B., & Nantajeewarawat, E. (2019). Rule-Based Polarity Aggregation Using Rhetorical Structures for Aspect-Based Sentiment Analysis. International Journal of Knowledge and Systems Science (IJKSS), 10(3), 44-60. http://doi.org/10.4018/IJKSS.2019070104

Chicago

Sanglerdsinlapachai, Nuttapong, et al. "Rule-Based Polarity Aggregation Using Rhetorical Structures for Aspect-Based Sentiment Analysis," International Journal of Knowledge and Systems Science (IJKSS) 10, no.3: 44-60. http://doi.org/10.4018/IJKSS.2019070104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The segments of a document that are relevant to a given aspect can be identified by using discourse relations of the rhetorical structure theory (RST). Different segments may contribute to the overall sentiment differently, and the sentiment of one segment may affect the contribution of another segment. This work exploits the RST structures of relevant segments to infer the sentiment of a given aspect. An input document is first parsed into an RST tree. For each aspect, relevant segments with their relations in the resulting tree are localized and transformed into a set of features. A set of classification rules is subsequently induced and evaluated on data. The proposed framework performs well in several experimental settings, with the accuracy values ranging from 74.0% to 77.1% being achieved. With proper strategies for removing conflicting rules and tuning the confidence threshold, f-measure values for the negative polarity class can be improved.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.