A hybrid method of domain lexicon construction for opinion targets extraction using syntax and semantics

Chun Liao*, Chong Feng, Sen Yang, Heyan Huang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Considering opinion targets extraction of Chinese microblogs plays an important role in opinion mining, there has been a significant progress in this area recently, especially the CRF-based method. However, this method only takes lexical-related features into consideration and does not excavate the implied semantic and syntactic knowledge. We propose a new approach which incorporates domain lexicon with groups of features using syntax and semantics. The approach acquires domain lexicon through a novel way namely PDSP. And then we combine the domain lexicon with opinion targets extracted from CRF with groups of features together for opinion targets extraction. Experimental results on COAE2014 dataset show that this approach notably outperforms other baselines of opinion targets extraction.

Original languageEnglish
Title of host publicationSocial Media Processing - 3rd National Conference, SMP 2014, Proceedings
EditorsJie Tang, Ting Liu, Heyan Huang, Hua-Ping Zhang
PublisherSpringer Verlag
Pages108-116
Number of pages9
ISBN (Electronic)9783662455579
DOIs
Publication statusPublished - 2014
Event3rd National Conference on Social Media Processing, SMP 2014 - Beijing, China
Duration: 1 Nov 20142 Nov 2014

Publication series

NameCommunications in Computer and Information Science
Volume489
ISSN (Print)1865-0929

Conference

Conference3rd National Conference on Social Media Processing, SMP 2014
Country/TerritoryChina
CityBeijing
Period1/11/142/11/14

Keywords

  • CRF
  • Domain lexicon
  • Groups of features
  • Opinion targets extraction

Fingerprint

Dive into the research topics of 'A hybrid method of domain lexicon construction for opinion targets extraction using syntax and semantics'. Together they form a unique fingerprint.

Cite this