Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review

Hai Ha Do, P. W.C. Prasad, Angelika Maag, Abeer Alsadoon

Research output: Contribution to journalReview article

2 Citations (Scopus)

Abstract

The increasing volume of user-generated content on the web has made sentiment analysis an important tool for the extraction of information about the human emotional state. A current research focus for sentiment analysis is the improvement of granularity at aspect level, representing two distinct aims: aspect extraction and sentiment classification of product reviews and sentiment classification of target-dependent tweets. Deep learning approaches have emerged as a prospect for achieving these aims with their ability to capture both syntactic and semantic features of text without requirements for high-level feature engineering, as is the case in earlier methods. In this article, we aim to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.

Original languageEnglish
Pages (from-to)272-299
Number of pages28
JournalExpert Systems with Applications
Volume118
DOIs
Publication statusPublished - 15 Mar 2019

Fingerprint

Syntactics
Semantics
Deep learning

Cite this

Do, Hai Ha ; Prasad, P. W.C. ; Maag, Angelika ; Alsadoon, Abeer. / Deep Learning for Aspect-Based Sentiment Analysis : A Comparative Review. In: Expert Systems with Applications. 2019 ; Vol. 118. pp. 272-299.
@article{5ae932b9f2c746468e829e2165f8429b,
title = "Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review",
abstract = "The increasing volume of user-generated content on the web has made sentiment analysis an important tool for the extraction of information about the human emotional state. A current research focus for sentiment analysis is the improvement of granularity at aspect level, representing two distinct aims: aspect extraction and sentiment classification of product reviews and sentiment classification of target-dependent tweets. Deep learning approaches have emerged as a prospect for achieving these aims with their ability to capture both syntactic and semantic features of text without requirements for high-level feature engineering, as is the case in earlier methods. In this article, we aim to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.",
author = "Do, {Hai Ha} and Prasad, {P. W.C.} and Angelika Maag and Abeer Alsadoon",
year = "2019",
month = "3",
day = "15",
doi = "10.1016/j.eswa.2018.10.003",
language = "English",
volume = "118",
pages = "272--299",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",

}

Deep Learning for Aspect-Based Sentiment Analysis : A Comparative Review. / Do, Hai Ha; Prasad, P. W.C.; Maag, Angelika; Alsadoon, Abeer.

In: Expert Systems with Applications, Vol. 118, 15.03.2019, p. 272-299.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Deep Learning for Aspect-Based Sentiment Analysis

T2 - A Comparative Review

AU - Do, Hai Ha

AU - Prasad, P. W.C.

AU - Maag, Angelika

AU - Alsadoon, Abeer

PY - 2019/3/15

Y1 - 2019/3/15

N2 - The increasing volume of user-generated content on the web has made sentiment analysis an important tool for the extraction of information about the human emotional state. A current research focus for sentiment analysis is the improvement of granularity at aspect level, representing two distinct aims: aspect extraction and sentiment classification of product reviews and sentiment classification of target-dependent tweets. Deep learning approaches have emerged as a prospect for achieving these aims with their ability to capture both syntactic and semantic features of text without requirements for high-level feature engineering, as is the case in earlier methods. In this article, we aim to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.

AB - The increasing volume of user-generated content on the web has made sentiment analysis an important tool for the extraction of information about the human emotional state. A current research focus for sentiment analysis is the improvement of granularity at aspect level, representing two distinct aims: aspect extraction and sentiment classification of product reviews and sentiment classification of target-dependent tweets. Deep learning approaches have emerged as a prospect for achieving these aims with their ability to capture both syntactic and semantic features of text without requirements for high-level feature engineering, as is the case in earlier methods. In this article, we aim to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.

UR - http://www.scopus.com/inward/record.url?scp=85054712386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054712386&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2018.10.003

DO - 10.1016/j.eswa.2018.10.003

M3 - Review article

VL - 118

SP - 272

EP - 299

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -