Skip to main navigation Skip to search Skip to main content

An enhanced framework for aspect-based sentiment analysis of Hotels' reviews: Arabic reviews case study

  • Mohammad Al-Smadi
  • , Omar Qwasmeh
  • , Bashar Talafha
  • , Mahmoud Al-Ayyoub
  • , Yaser Jararweh
  • , Elhadj Benkhelifa
  • Jordan University of Science and Technology
  • University of Staffordshire

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

52 Scopus citations

Abstract

This research proposes a framework for aspect-based sentiment analysis (ABSA) of Hotels' reviews. The proposed framework consists of: (a) a reference human annotated Arabic dataset to support ABSA tasks such as aspect category identification, opinion target expression extraction, and opinion sentiment polarity. The dataset was annotated on both sentence-level and text-level, (b) baseline approach where a Support Vector Machine (SVM) was trained as part of the ABSA tasks, (c) baseline experiments and results, and (d) a common evaluation technique to provide a unified evaluation of future research working on the same dataset and ABSA tasks.

Original languageEnglish
Title of host publication2016 11th International Conference for Internet Technology and Secured Transactions, ICITST 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages98-103
Number of pages6
ISBN (Electronic)9781908320735
DOIs
StatePublished - 14 Feb 2017
Externally publishedYes
Event11th International Conference for Internet Technology and Secured Transactions, ICITST 2016 - Barcelona, Spain
Duration: 5 Dec 20167 Dec 2016

Publication series

Name2016 11th International Conference for Internet Technology and Secured Transactions, ICITST 2016

Conference

Conference11th International Conference for Internet Technology and Secured Transactions, ICITST 2016
Country/TerritorySpain
CityBarcelona
Period5/12/167/12/16

Fingerprint

Dive into the research topics of 'An enhanced framework for aspect-based sentiment analysis of Hotels' reviews: Arabic reviews case study'. Together they form a unique fingerprint.

Cite this