Rule-Based Polarity Aggregation Using Rhetorical Structures for Aspect-Based Sentiment Analysis
Autor: | Tu Bao Ho, Anon Plangprasopchok, Ekawit Nantajeewarawat, Nuttapong Sanglerdsinlapachai |
---|---|
Rok vydání: | 2019 |
Předmět: |
Organizational Behavior and Human Resource Management
Information Systems and Management Polarity (physics) Computer science business.industry Strategy and Management Sentiment analysis Rule-based system 02 engineering and technology computer.software_genre Artificial Intelligence 020204 information systems Management of Technology and Innovation 0202 electrical engineering electronic engineering information engineering Rhetorical question 020201 artificial intelligence & image processing Artificial intelligence business computer Natural language processing Information Systems |
Zdroj: | International Journal of Knowledge and Systems Science. 10:44-60 |
ISSN: | 1947-8216 1947-8208 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |