Fine-grained product feature extraction in Chinese reviews

Hanqian Wu, Tao Liu, Jue Xie

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

Abstract

Fine-grained product feature extraction is the most important task in opinion mining. To realize the fine-grained product feature extraction in Chinese reviews, three main tasks have been solved in this paper. Firstly, we propose a dependency parsing based method to directly extract the explicit feature-opinion pairs. Then, by analyzing the characteristics of two synonyms features and the relations with opinion words, we calculate the similarities to cluster features. Finally, we propose a novel implicit feature extraction method by combining review context information and two kind opinions to extract implicit features. Experiments show that the dependency parsing based method can get high precision, by considering verbs as product feature can improve the recall obviously. Besides, several proven pruning strategies can improve the accuracy. The comparison demonstrates that our implicit feature extraction method outperforms existing method, and feature clustering before implicit feature mining can get better results.

Original languageEnglish
Title of host publicationProceedings - 2017 International Conference on Computing Intelligence and Information System, CIIS 2017
EditorsMichael Negnevitsky
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages327-331
Number of pages5
ISBN (Electronic)9781538638866
ISBN (Print)9781538638804
DOIs
Publication statusPublished - 2017
EventInternational Conference on Computing Intelligence and Information System 2017 - Nanjing, Jiangsu, China
Duration: 21 Apr 201723 Apr 2017
https://www.computer.org/csdl/proceedings/ciis/2017/12OmNz2kqrp

Conference

ConferenceInternational Conference on Computing Intelligence and Information System 2017
Abbreviated titleCIIS 2017
CountryChina
CityNanjing, Jiangsu
Period21/04/1723/04/17
Internet address

Keywords

  • dependency parsing
  • Explicit feature
  • Feature clustering
  • Implicit feature

Cite this