Feature-Level Sentiment Analysis Based on Rules and Fine-Grained Domain Ontology

Wie Wei; Yi-Ping Liu; Lei-Ru Wei

doi:10.5771/0943-7444-2020-2-105

Contents
- Chapter Expand | CollapseAuthorsPage
- I–II Titelei/Inhaltsverzeichnis I–II
- 103–103 16th International ISKO Conference (Aalborg, Denmark, 6-8 July 2020) 103–103
- 104–104 General Assembly July 2020. Provisional Agenda 104–104
- 105–172 Articles 105–172
  - 105–121 Feature-Level Sentiment Analysis Based on Rules and Fine-Grained Domain Ontology Wie Wei, Yi-Ping Liu, Lei-Ru Wei Wie Wei, Yi-Ping Liu, Lei-Ru Wei 105–121
  - 122–137 Towards a Vocabulary to Implement Culturally Relevant Relationships Between Digital Collections in Heritage Institutions Carlos H. Marcondes Carlos H. Marcondes 122–137
  - 138–159 A Systematic Analysis of Flood Ontologies: A Parametric Approach Prasant Kumar Sinha, Biswanath Dutta Prasant Kumar Sinha, Biswanath Dutta 138–159
  - 160–172 The Sociological and Ontological Dimensions of the Knowledge Organization Domain on Google Scholar Citations Marcin Roszkowski Marcin Roszkowski 160–172
- 173–194 Reviews of Concepts in Knowledge Organization 173–194
  - 173–182 Ingetraut Dahlberg (1927-2017) Peter Ohly Peter Ohly 173–182
  - 183–194 Nomenclature for Museum Cataloging Heather Dunn, Paul Bourcier Heather Dunn, Paul Bourcier 183–194
- 195–195 Books Recently Published 195–195
Durchsuchen Sie das Werk
Geben Sie ein Keyword in die Suchleiste ein
No access

KO KNOWLEDGE ORGANIZATION , page 105 - 121

Feature-Level Sentiment Analysis Based on Rules and Fine-Grained Domain Ontology

Autoren

Wie Wei Yi-Ping Liu Lei-Ru Wei

DOI
- doi.org/10.5771/0943-7444-2020-2-105
- ISSN: 0943-7444
- ISSN online: 2942-3309
Abstract

Mining product reviews and sentiment analysis are of great significance, whether for academic research purposes or optimizing business strategies. We propose a feature-level sentiment analysis framework based on rules parsing and fine-grained domain ontology for Chinese reviews. Fine-grained ontology is used to describe synonymous expressions of product features, which are reflected in word changes in online reviews. First, a semiautomatic construction method is developed by using Word2Vec for fine-grained ontology. Then, feature-level sentiment analysis that combines rules parsing and the fine-grained domain ontology is conducted to extract explicit and implicit features from product reviews. Finally, the domain sentiment dictionary and context sentiment dictionary are established to identify sentiment polarities for the extracted feature-sentiment combinations. An experiment is conducted on the basis of product reviews crawled from Chinese e-commerce websites. The results demonstrate the effectiveness of our approach.
Share