Sentiment Strength Detection With a Context-dependent Lexicon-based Convolutional Neural Network

Minghui HUANG, Haoran XIE, Yanghui RAO, Jingrong FENG, Fu Lee WANG

Research output: Journal PublicationsJournal Article (refereed)

Abstract

Sentiment strength detection is an essential task in sentiment analysis, wherein the sentiment strength of subjective text is automatically determined. Sentiment analysis has numerous applications in different sectors, including business and social domains. In this study, we present a model to effectively extract the features and strength of sentiment from words and text using a context-dependent, lexicon-based convolutional neural network. To build this convolutional neural network, the model is trained using the sentiment polarity for each word from a co-occurrence pattern of words and labels. Then, a context-dependent lexicon is generated from the corpus, which is used to generate positive and negative sentiment word embeddings. Positive sentiment word embeddings, negative sentiment word embeddings, and the pre-trained word embeddings are input to a 3-channel convolutional neural network (CNN) to predict the strength of the sentiments. Moreover, with the trained convolutional neural network model, we can obtain a learned sentiment strength-specific word embedding, which generates a sentiment strength-specific lexicon (SSS-Lex) that contains word associations and sentiment intensity scores. To validate the effectiveness of sentiment strength detection in the proposed model, we evaluate the model using six real-world datasets. Furthermore, to evaluate the sentiment strength-specific lexicon, we compare it with seven existing lexicons in three evaluation tasks from the SemEval-2015 and SemEval-2016 competitions. Experimental results indicate that the proposed model can predict the sentiment strength of documents more effectively than the baseline methods, and that the SSS-Lex is of higher quality than the existing lexicons.
Original languageEnglish
JournalInformation Sciences
DOIs
Publication statusE-pub ahead of print - 10 Feb 2020

Fingerprint

Neural Networks
Neural networks
Dependent
Sentiment Analysis
Context
Sentiment
Labels
Predict
Model
Evaluate
Polarity
Neural Network Model
Baseline
Sector
Industry
Evaluation
Experimental Results

Bibliographical note

The work described in this paper was fully supported by the Innovation and Technology Fund (Project No. GHP/022/17GD) from the Innovation and Technology Commission of the Government of the Hong Kong Special Administrative Region, HKIBS Research Seed Fund 2019/2020 (HKIBS RSF-190-009) of Lingnan University, Hong Kong.

Keywords

  • Sentiment strength detection
  • sentiment analysis
  • text mining
  • convolutional neural network
  • sentiment strength-specific lexicon

Cite this

@article{43ad04e672ad46d787d828a617063b25,
title = "Sentiment Strength Detection With a Context-dependent Lexicon-based Convolutional Neural Network",
abstract = "Sentiment strength detection is an essential task in sentiment analysis, wherein the sentiment strength of subjective text is automatically determined. Sentiment analysis has numerous applications in different sectors, including business and social domains. In this study, we present a model to effectively extract the features and strength of sentiment from words and text using a context-dependent, lexicon-based convolutional neural network. To build this convolutional neural network, the model is trained using the sentiment polarity for each word from a co-occurrence pattern of words and labels. Then, a context-dependent lexicon is generated from the corpus, which is used to generate positive and negative sentiment word embeddings. Positive sentiment word embeddings, negative sentiment word embeddings, and the pre-trained word embeddings are input to a 3-channel convolutional neural network (CNN) to predict the strength of the sentiments. Moreover, with the trained convolutional neural network model, we can obtain a learned sentiment strength-specific word embedding, which generates a sentiment strength-specific lexicon (SSS-Lex) that contains word associations and sentiment intensity scores. To validate the effectiveness of sentiment strength detection in the proposed model, we evaluate the model using six real-world datasets. Furthermore, to evaluate the sentiment strength-specific lexicon, we compare it with seven existing lexicons in three evaluation tasks from the SemEval-2015 and SemEval-2016 competitions. Experimental results indicate that the proposed model can predict the sentiment strength of documents more effectively than the baseline methods, and that the SSS-Lex is of higher quality than the existing lexicons.",
keywords = "Sentiment strength detection, sentiment analysis, text mining, convolutional neural network, sentiment strength-specific lexicon",
author = "Minghui HUANG and Haoran XIE and Yanghui RAO and Jingrong FENG and WANG, {Fu Lee}",
note = "The work described in this paper was fully supported by the Innovation and Technology Fund (Project No. GHP/022/17GD) from the Innovation and Technology Commission of the Government of the Hong Kong Special Administrative Region, HKIBS Research Seed Fund 2019/2020 (HKIBS RSF-190-009) of Lingnan University, Hong Kong.",
year = "2020",
month = "2",
day = "10",
doi = "10.1016/j.ins.2020.02.026",
language = "English",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

Sentiment Strength Detection With a Context-dependent Lexicon-based Convolutional Neural Network. / HUANG, Minghui; XIE, Haoran; RAO, Yanghui; FENG, Jingrong; WANG, Fu Lee.

In: Information Sciences, 10.02.2020.

Research output: Journal PublicationsJournal Article (refereed)

TY - JOUR

T1 - Sentiment Strength Detection With a Context-dependent Lexicon-based Convolutional Neural Network

AU - HUANG, Minghui

AU - XIE, Haoran

AU - RAO, Yanghui

AU - FENG, Jingrong

AU - WANG, Fu Lee

N1 - The work described in this paper was fully supported by the Innovation and Technology Fund (Project No. GHP/022/17GD) from the Innovation and Technology Commission of the Government of the Hong Kong Special Administrative Region, HKIBS Research Seed Fund 2019/2020 (HKIBS RSF-190-009) of Lingnan University, Hong Kong.

PY - 2020/2/10

Y1 - 2020/2/10

N2 - Sentiment strength detection is an essential task in sentiment analysis, wherein the sentiment strength of subjective text is automatically determined. Sentiment analysis has numerous applications in different sectors, including business and social domains. In this study, we present a model to effectively extract the features and strength of sentiment from words and text using a context-dependent, lexicon-based convolutional neural network. To build this convolutional neural network, the model is trained using the sentiment polarity for each word from a co-occurrence pattern of words and labels. Then, a context-dependent lexicon is generated from the corpus, which is used to generate positive and negative sentiment word embeddings. Positive sentiment word embeddings, negative sentiment word embeddings, and the pre-trained word embeddings are input to a 3-channel convolutional neural network (CNN) to predict the strength of the sentiments. Moreover, with the trained convolutional neural network model, we can obtain a learned sentiment strength-specific word embedding, which generates a sentiment strength-specific lexicon (SSS-Lex) that contains word associations and sentiment intensity scores. To validate the effectiveness of sentiment strength detection in the proposed model, we evaluate the model using six real-world datasets. Furthermore, to evaluate the sentiment strength-specific lexicon, we compare it with seven existing lexicons in three evaluation tasks from the SemEval-2015 and SemEval-2016 competitions. Experimental results indicate that the proposed model can predict the sentiment strength of documents more effectively than the baseline methods, and that the SSS-Lex is of higher quality than the existing lexicons.

AB - Sentiment strength detection is an essential task in sentiment analysis, wherein the sentiment strength of subjective text is automatically determined. Sentiment analysis has numerous applications in different sectors, including business and social domains. In this study, we present a model to effectively extract the features and strength of sentiment from words and text using a context-dependent, lexicon-based convolutional neural network. To build this convolutional neural network, the model is trained using the sentiment polarity for each word from a co-occurrence pattern of words and labels. Then, a context-dependent lexicon is generated from the corpus, which is used to generate positive and negative sentiment word embeddings. Positive sentiment word embeddings, negative sentiment word embeddings, and the pre-trained word embeddings are input to a 3-channel convolutional neural network (CNN) to predict the strength of the sentiments. Moreover, with the trained convolutional neural network model, we can obtain a learned sentiment strength-specific word embedding, which generates a sentiment strength-specific lexicon (SSS-Lex) that contains word associations and sentiment intensity scores. To validate the effectiveness of sentiment strength detection in the proposed model, we evaluate the model using six real-world datasets. Furthermore, to evaluate the sentiment strength-specific lexicon, we compare it with seven existing lexicons in three evaluation tasks from the SemEval-2015 and SemEval-2016 competitions. Experimental results indicate that the proposed model can predict the sentiment strength of documents more effectively than the baseline methods, and that the SSS-Lex is of higher quality than the existing lexicons.

KW - Sentiment strength detection

KW - sentiment analysis

KW - text mining

KW - convolutional neural network

KW - sentiment strength-specific lexicon

U2 - 10.1016/j.ins.2020.02.026

DO - 10.1016/j.ins.2020.02.026

M3 - Journal Article (refereed)

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -