Successes and challenges in developing a hybrid approach to sentiment analysis

Orestes Appel, Francisco Chiclana, Jenny Carter, Hamido Fujita

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This article covers some success and learning experiences attained during the developing of a hybrid approach to Sentiment Analysis (SA) based on a Sentiment Lexicon, Semantic Rules, Negation Handling, Ambiguity Management and Linguistic Variables. The proposed hybrid method is presented and applied to two selected datasets: Movie Review and Sentiment Twitter datasets. The achieved results are compared against those obtained when Naïve Bayes (NB) and Maximum Entropy (ME) supervised machine learning classification methods are used for the same datasets. The proposed hybrid system attained higher accuracy and precision scores than NB and ME, which shows its superiority when applied to the SA problem at the sentence level. Finally, an alternative strategy to calculating the orientation polarity and polarity intensity in one step instead of the two steps method used in the hybrid approach is explored. The analysis of the yielded mixed results achieved with this alternative approach shows its potential as an aid in the computation of semantic orientations and produced some lessons learnt in developing a more effective mechanism to calculating the orientation polarity and polarity intensity.
Original languageEnglish
Pages (from-to)1176-1188
Number of pages13
JournalApplied Intelligence
Volume48
Issue number5
Early online date20 Jun 2017
DOIs
Publication statusPublished - May 2018
Externally publishedYes

Fingerprint

Entropy
Semantics
Hybrid systems
Linguistics
Learning systems

Cite this

Appel, Orestes ; Chiclana, Francisco ; Carter, Jenny ; Fujita, Hamido. / Successes and challenges in developing a hybrid approach to sentiment analysis. In: Applied Intelligence. 2018 ; Vol. 48, No. 5. pp. 1176-1188.
@article{214e13249d8c48429b0d9a32c0d95bab,
title = "Successes and challenges in developing a hybrid approach to sentiment analysis",
abstract = "This article covers some success and learning experiences attained during the developing of a hybrid approach to Sentiment Analysis (SA) based on a Sentiment Lexicon, Semantic Rules, Negation Handling, Ambiguity Management and Linguistic Variables. The proposed hybrid method is presented and applied to two selected datasets: Movie Review and Sentiment Twitter datasets. The achieved results are compared against those obtained when Na{\"i}ve Bayes (NB) and Maximum Entropy (ME) supervised machine learning classification methods are used for the same datasets. The proposed hybrid system attained higher accuracy and precision scores than NB and ME, which shows its superiority when applied to the SA problem at the sentence level. Finally, an alternative strategy to calculating the orientation polarity and polarity intensity in one step instead of the two steps method used in the hybrid approach is explored. The analysis of the yielded mixed results achieved with this alternative approach shows its potential as an aid in the computation of semantic orientations and produced some lessons learnt in developing a more effective mechanism to calculating the orientation polarity and polarity intensity.",
keywords = "Computational linguistic, Computing with sentiments, Fuzzy sets, Natural language processing, Semantic rules, Sentiment analysis, SentiWordNet, Uninorms",
author = "Orestes Appel and Francisco Chiclana and Jenny Carter and Hamido Fujita",
year = "2018",
month = "5",
doi = "10.1007/s10489-017-0966-4",
language = "English",
volume = "48",
pages = "1176--1188",
journal = "Applied Intelligence",
issn = "0924-669X",
publisher = "Springer Netherlands",
number = "5",

}

Successes and challenges in developing a hybrid approach to sentiment analysis. / Appel, Orestes; Chiclana, Francisco; Carter, Jenny; Fujita, Hamido.

In: Applied Intelligence, Vol. 48, No. 5, 05.2018, p. 1176-1188.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Successes and challenges in developing a hybrid approach to sentiment analysis

AU - Appel, Orestes

AU - Chiclana, Francisco

AU - Carter, Jenny

AU - Fujita, Hamido

PY - 2018/5

Y1 - 2018/5

N2 - This article covers some success and learning experiences attained during the developing of a hybrid approach to Sentiment Analysis (SA) based on a Sentiment Lexicon, Semantic Rules, Negation Handling, Ambiguity Management and Linguistic Variables. The proposed hybrid method is presented and applied to two selected datasets: Movie Review and Sentiment Twitter datasets. The achieved results are compared against those obtained when Naïve Bayes (NB) and Maximum Entropy (ME) supervised machine learning classification methods are used for the same datasets. The proposed hybrid system attained higher accuracy and precision scores than NB and ME, which shows its superiority when applied to the SA problem at the sentence level. Finally, an alternative strategy to calculating the orientation polarity and polarity intensity in one step instead of the two steps method used in the hybrid approach is explored. The analysis of the yielded mixed results achieved with this alternative approach shows its potential as an aid in the computation of semantic orientations and produced some lessons learnt in developing a more effective mechanism to calculating the orientation polarity and polarity intensity.

AB - This article covers some success and learning experiences attained during the developing of a hybrid approach to Sentiment Analysis (SA) based on a Sentiment Lexicon, Semantic Rules, Negation Handling, Ambiguity Management and Linguistic Variables. The proposed hybrid method is presented and applied to two selected datasets: Movie Review and Sentiment Twitter datasets. The achieved results are compared against those obtained when Naïve Bayes (NB) and Maximum Entropy (ME) supervised machine learning classification methods are used for the same datasets. The proposed hybrid system attained higher accuracy and precision scores than NB and ME, which shows its superiority when applied to the SA problem at the sentence level. Finally, an alternative strategy to calculating the orientation polarity and polarity intensity in one step instead of the two steps method used in the hybrid approach is explored. The analysis of the yielded mixed results achieved with this alternative approach shows its potential as an aid in the computation of semantic orientations and produced some lessons learnt in developing a more effective mechanism to calculating the orientation polarity and polarity intensity.

KW - Computational linguistic

KW - Computing with sentiments

KW - Fuzzy sets

KW - Natural language processing

KW - Semantic rules

KW - Sentiment analysis

KW - SentiWordNet

KW - Uninorms

UR - http://www.scopus.com/inward/record.url?scp=85021056017&partnerID=8YFLogxK

U2 - 10.1007/s10489-017-0966-4

DO - 10.1007/s10489-017-0966-4

M3 - Article

VL - 48

SP - 1176

EP - 1188

JO - Applied Intelligence

JF - Applied Intelligence

SN - 0924-669X

IS - 5

ER -