Use of multi-lexicons to analyse semantic features for summarization of touring reviews

Hei-Chia Wang, Yu Hung Chiang, Yi Feng Sun

Research output: Contribution to journalArticle

Abstract

Purpose: This paper aims to improve a sentiment analysis (SA) system to help users (i.e. customers or hotel managers) understand hotel evaluations. There are three main purposes in this paper: designing an unsupervised method for extracting online Chinese features and opinion pairs, distinguishing different intensities of polarity in opinion words and examining the changes in polarity in the time series. Design/methodology/approach: In this paper, a review analysis system is proposed to automatically capture feature opinions experienced by other tourists presented in the review documents. In the system, a feature-level SA is designed to determine the polarity of these features. Moreover, an unsupervised method using a part-of-speech pattern clarification query and multi-lexicons SA to summarize all Chinese reviews is adopted. Findings: The authors expect this method to help travellers search for what they want and make decisions more efficiently. The experimental results show the F-measure of the proposed method to be 0.628. It thus outperforms the methods used in previous studies. Originality/value: The study is useful for travellers who want to quickly retrieve and summarize helpful information from the pool of messy hotel reviews. Meanwhile, the system will assist hotel managers to comprehensively understand service qualities with which guests are satisfied or dissatisfied.

Original languageEnglish
Pages (from-to)185-206
Number of pages22
JournalElectronic Library
Volume37
Issue number1
DOIs
Publication statusPublished - 2019 Feb 4

Fingerprint

Hotels
Semantics
semantics
systems analysis
Managers
manager
Time series
time series
tourist
customer
methodology
evaluation
Values

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Library and Information Sciences

Cite this

Wang, Hei-Chia ; Chiang, Yu Hung ; Sun, Yi Feng. / Use of multi-lexicons to analyse semantic features for summarization of touring reviews. In: Electronic Library. 2019 ; Vol. 37, No. 1. pp. 185-206.
@article{8d3a01b310154aaaa8039db85286d297,
title = "Use of multi-lexicons to analyse semantic features for summarization of touring reviews",
abstract = "Purpose: This paper aims to improve a sentiment analysis (SA) system to help users (i.e. customers or hotel managers) understand hotel evaluations. There are three main purposes in this paper: designing an unsupervised method for extracting online Chinese features and opinion pairs, distinguishing different intensities of polarity in opinion words and examining the changes in polarity in the time series. Design/methodology/approach: In this paper, a review analysis system is proposed to automatically capture feature opinions experienced by other tourists presented in the review documents. In the system, a feature-level SA is designed to determine the polarity of these features. Moreover, an unsupervised method using a part-of-speech pattern clarification query and multi-lexicons SA to summarize all Chinese reviews is adopted. Findings: The authors expect this method to help travellers search for what they want and make decisions more efficiently. The experimental results show the F-measure of the proposed method to be 0.628. It thus outperforms the methods used in previous studies. Originality/value: The study is useful for travellers who want to quickly retrieve and summarize helpful information from the pool of messy hotel reviews. Meanwhile, the system will assist hotel managers to comprehensively understand service qualities with which guests are satisfied or dissatisfied.",
author = "Hei-Chia Wang and Chiang, {Yu Hung} and Sun, {Yi Feng}",
year = "2019",
month = "2",
day = "4",
doi = "10.1108/EL-11-2018-0215",
language = "English",
volume = "37",
pages = "185--206",
journal = "Electronic Library",
issn = "0264-0473",
publisher = "Emerald Group Publishing Ltd.",
number = "1",

}

Use of multi-lexicons to analyse semantic features for summarization of touring reviews. / Wang, Hei-Chia; Chiang, Yu Hung; Sun, Yi Feng.

In: Electronic Library, Vol. 37, No. 1, 04.02.2019, p. 185-206.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Use of multi-lexicons to analyse semantic features for summarization of touring reviews

AU - Wang, Hei-Chia

AU - Chiang, Yu Hung

AU - Sun, Yi Feng

PY - 2019/2/4

Y1 - 2019/2/4

N2 - Purpose: This paper aims to improve a sentiment analysis (SA) system to help users (i.e. customers or hotel managers) understand hotel evaluations. There are three main purposes in this paper: designing an unsupervised method for extracting online Chinese features and opinion pairs, distinguishing different intensities of polarity in opinion words and examining the changes in polarity in the time series. Design/methodology/approach: In this paper, a review analysis system is proposed to automatically capture feature opinions experienced by other tourists presented in the review documents. In the system, a feature-level SA is designed to determine the polarity of these features. Moreover, an unsupervised method using a part-of-speech pattern clarification query and multi-lexicons SA to summarize all Chinese reviews is adopted. Findings: The authors expect this method to help travellers search for what they want and make decisions more efficiently. The experimental results show the F-measure of the proposed method to be 0.628. It thus outperforms the methods used in previous studies. Originality/value: The study is useful for travellers who want to quickly retrieve and summarize helpful information from the pool of messy hotel reviews. Meanwhile, the system will assist hotel managers to comprehensively understand service qualities with which guests are satisfied or dissatisfied.

AB - Purpose: This paper aims to improve a sentiment analysis (SA) system to help users (i.e. customers or hotel managers) understand hotel evaluations. There are three main purposes in this paper: designing an unsupervised method for extracting online Chinese features and opinion pairs, distinguishing different intensities of polarity in opinion words and examining the changes in polarity in the time series. Design/methodology/approach: In this paper, a review analysis system is proposed to automatically capture feature opinions experienced by other tourists presented in the review documents. In the system, a feature-level SA is designed to determine the polarity of these features. Moreover, an unsupervised method using a part-of-speech pattern clarification query and multi-lexicons SA to summarize all Chinese reviews is adopted. Findings: The authors expect this method to help travellers search for what they want and make decisions more efficiently. The experimental results show the F-measure of the proposed method to be 0.628. It thus outperforms the methods used in previous studies. Originality/value: The study is useful for travellers who want to quickly retrieve and summarize helpful information from the pool of messy hotel reviews. Meanwhile, the system will assist hotel managers to comprehensively understand service qualities with which guests are satisfied or dissatisfied.

UR - http://www.scopus.com/inward/record.url?scp=85063876946&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063876946&partnerID=8YFLogxK

U2 - 10.1108/EL-11-2018-0215

DO - 10.1108/EL-11-2018-0215

M3 - Article

VL - 37

SP - 185

EP - 206

JO - Electronic Library

JF - Electronic Library

SN - 0264-0473

IS - 1

ER -