ECNU: Extracting Effective Features from Multiple Sequential Sentences for Target-dependent Sentiment Analysis in Reviews

  • Zhihua Zhang
  • , Man Lan*
  • *Corresponding author for this work

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

29 Scopus citations

Abstract

This paper describes our systems submitted to the target-dependent sentiment polarity classification subtask in aspect based sentiment analysis (ABSA) task (i.e., Task 12) in SemEval 2015. To settle this problem, we extracted several effective features from three sequential sentences, including sentiment lexicon, linguistic and domain specific features. Then we employed these features to construct classifiers using supervised classification algorithm. In laptop domain, our systems ranked 2nd out of 6 constrained submissions and 2nd out of 7 unconstrained submissions. In restaurant domain, the rankings are 5th out of 6 and 2nd out of 8 respectively.

Original languageEnglish
Title of host publicationSemEval 2015 - 9th International Workshop on Semantic Evaluation, co-located with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, NAACL-HLT 2015 - Proceedings
EditorsPreslav Nakov, Torsten Zesch, Daniel Cer, David Jurgens
PublisherAssociation for Computational Linguistics (ACL)
Pages736-741
Number of pages6
ISBN (Electronic)9781941643402
DOIs
StatePublished - 2015
Event9th International Workshop on Semantic Evaluation, SemEval 2015 co-located with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015 - Denver, United States
Duration: 4 Jun 20155 Jun 2015

Publication series

NameSemEval 2015 - 9th International Workshop on Semantic Evaluation, co-located with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015 - Proceedings

Conference

Conference9th International Workshop on Semantic Evaluation, SemEval 2015 co-located with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015
Country/TerritoryUnited States
CityDenver
Period4/06/155/06/15

Fingerprint

Dive into the research topics of 'ECNU: Extracting Effective Features from Multiple Sequential Sentences for Target-dependent Sentiment Analysis in Reviews'. Together they form a unique fingerprint.

Cite this