Approaches to Cross-Domain Sentiment Analysis: A Systematic Literature Review

Tareq Al-Moslmi, Nazlia Omar, Salwani Abdullah, Mohammed Albared

Research output: Contribution to journalReview article

22 Citations (Scopus)

Abstract

A sentiment analysis has received a lot of attention from researchers working in the fields of natural language processing and text mining. However, there is a lack of annotated data sets that can be used to train a model for all domains, which is hampering the accuracy of sentiment analysis. Many research studies have attempted to tackle this issue and to improve cross-domain sentiment classification. In this paper, we present the results of a comprehensive systematic literature review of the methods and techniques employed in a cross-domain sentiment analysis. We focus on studies published during the period of 2010-2016. From our analysis of those works, it is clear that there is no perfect solution. Hence, one of the aims of this review is to create a resource in the form of an overview of the techniques, methods, and approaches that have been used to attempt to solve the problem of cross-domain sentiment analysis in order to assist researchers in developing new and more accurate techniques in the future.

Original languageEnglish
Article number7891035
Pages (from-to)16173-16192
Number of pages20
JournalIEEE Access
Volume5
DOIs
Publication statusPublished - 2017

Fingerprint

Processing

Keywords

  • Cross-domain sentiment analysis
  • domain adaptation for sentiment analysis
  • multi-domain sentiment analysis
  • sentiment analysis
  • systematic literature review
  • transfer learning

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Approaches to Cross-Domain Sentiment Analysis : A Systematic Literature Review. / Al-Moslmi, Tareq; Omar, Nazlia; Abdullah, Salwani; Albared, Mohammed.

In: IEEE Access, Vol. 5, 7891035, 2017, p. 16173-16192.

Research output: Contribution to journalReview article

@article{860e492cbfc9416ca755f40c264eeda1,
title = "Approaches to Cross-Domain Sentiment Analysis: A Systematic Literature Review",
abstract = "A sentiment analysis has received a lot of attention from researchers working in the fields of natural language processing and text mining. However, there is a lack of annotated data sets that can be used to train a model for all domains, which is hampering the accuracy of sentiment analysis. Many research studies have attempted to tackle this issue and to improve cross-domain sentiment classification. In this paper, we present the results of a comprehensive systematic literature review of the methods and techniques employed in a cross-domain sentiment analysis. We focus on studies published during the period of 2010-2016. From our analysis of those works, it is clear that there is no perfect solution. Hence, one of the aims of this review is to create a resource in the form of an overview of the techniques, methods, and approaches that have been used to attempt to solve the problem of cross-domain sentiment analysis in order to assist researchers in developing new and more accurate techniques in the future.",
keywords = "Cross-domain sentiment analysis, domain adaptation for sentiment analysis, multi-domain sentiment analysis, sentiment analysis, systematic literature review, transfer learning",
author = "Tareq Al-Moslmi and Nazlia Omar and Salwani Abdullah and Mohammed Albared",
year = "2017",
doi = "10.1109/ACCESS.2017.2690342",
language = "English",
volume = "5",
pages = "16173--16192",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Approaches to Cross-Domain Sentiment Analysis

T2 - A Systematic Literature Review

AU - Al-Moslmi, Tareq

AU - Omar, Nazlia

AU - Abdullah, Salwani

AU - Albared, Mohammed

PY - 2017

Y1 - 2017

N2 - A sentiment analysis has received a lot of attention from researchers working in the fields of natural language processing and text mining. However, there is a lack of annotated data sets that can be used to train a model for all domains, which is hampering the accuracy of sentiment analysis. Many research studies have attempted to tackle this issue and to improve cross-domain sentiment classification. In this paper, we present the results of a comprehensive systematic literature review of the methods and techniques employed in a cross-domain sentiment analysis. We focus on studies published during the period of 2010-2016. From our analysis of those works, it is clear that there is no perfect solution. Hence, one of the aims of this review is to create a resource in the form of an overview of the techniques, methods, and approaches that have been used to attempt to solve the problem of cross-domain sentiment analysis in order to assist researchers in developing new and more accurate techniques in the future.

AB - A sentiment analysis has received a lot of attention from researchers working in the fields of natural language processing and text mining. However, there is a lack of annotated data sets that can be used to train a model for all domains, which is hampering the accuracy of sentiment analysis. Many research studies have attempted to tackle this issue and to improve cross-domain sentiment classification. In this paper, we present the results of a comprehensive systematic literature review of the methods and techniques employed in a cross-domain sentiment analysis. We focus on studies published during the period of 2010-2016. From our analysis of those works, it is clear that there is no perfect solution. Hence, one of the aims of this review is to create a resource in the form of an overview of the techniques, methods, and approaches that have been used to attempt to solve the problem of cross-domain sentiment analysis in order to assist researchers in developing new and more accurate techniques in the future.

KW - Cross-domain sentiment analysis

KW - domain adaptation for sentiment analysis

KW - multi-domain sentiment analysis

KW - sentiment analysis

KW - systematic literature review

KW - transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85029659979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029659979&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2017.2690342

DO - 10.1109/ACCESS.2017.2690342

M3 - Review article

AN - SCOPUS:85029659979

VL - 5

SP - 16173

EP - 16192

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 7891035

ER -