Comparative Study of Deep Learning-Based Sentiment Classification

The purpose of sentiment classification is to determine whether a particular document has a positive or negative nuance. Sentiment classification is extensively used in many business domains to improve products or services by understanding the opinions of customers regarding these products. Deep lea...

Full description

Saved in:
Bibliographic Details
Main Authors: Seungwan Seo, Czangyeob Kim, Haedong Kim, Kyounghyun Mo, Pilsung Kang
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8948030/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850190895110946816
author Seungwan Seo
Czangyeob Kim
Haedong Kim
Kyounghyun Mo
Pilsung Kang
author_facet Seungwan Seo
Czangyeob Kim
Haedong Kim
Kyounghyun Mo
Pilsung Kang
author_sort Seungwan Seo
collection DOAJ
description The purpose of sentiment classification is to determine whether a particular document has a positive or negative nuance. Sentiment classification is extensively used in many business domains to improve products or services by understanding the opinions of customers regarding these products. Deep learning achieves state-of-the-art results in various challenging domains. With the success of deep learning, many studies have proposed deep-learning-based sentiment classification models and achieved better performances compared with conventional machine learning models. However, one practical issue occurring in deep-learning-based sentiment classification is that the best model structure depends on the characteristics of the dataset on which the deep learning model is trained; moreover, it is manually determined based on the domain knowledge of an expert or selected from a grid search of possible candidates. Herein, we present a comparative study of different deep-learning-based sentiment classification model structures to derive meaningful implications for building sentiment classification models. Specifically, eight deep-learning models, three based on convolutional neural networks and five based on recurrent neural networks, with two types of input structures, i.e., word level and character level, are compared for 13 review datasets, and the classification performances are discussed under different perspectives.
format Article
id doaj-art-86ba8a29f9764b72937a7f6d624bef45
institution OA Journals
issn 2169-3536
language English
publishDate 2020-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-86ba8a29f9764b72937a7f6d624bef452025-08-20T02:15:07ZengIEEEIEEE Access2169-35362020-01-0186861687510.1109/ACCESS.2019.29634268948030Comparative Study of Deep Learning-Based Sentiment ClassificationSeungwan Seo0Czangyeob Kim1Haedong Kim2Kyounghyun Mo3Pilsung Kang4https://orcid.org/0000-0001-7663-3937School of Industrial Management Engineering, Korea University, Seoul, South KoreaSchool of Industrial Management Engineering, Korea University, Seoul, South KoreaDepartment of Industrial and Manufacturing Engineering, The Pennsylvania State University, State College, PA, USASK C&C, Seoul, South KoreaSchool of Industrial Management Engineering, Korea University, Seoul, South KoreaThe purpose of sentiment classification is to determine whether a particular document has a positive or negative nuance. Sentiment classification is extensively used in many business domains to improve products or services by understanding the opinions of customers regarding these products. Deep learning achieves state-of-the-art results in various challenging domains. With the success of deep learning, many studies have proposed deep-learning-based sentiment classification models and achieved better performances compared with conventional machine learning models. However, one practical issue occurring in deep-learning-based sentiment classification is that the best model structure depends on the characteristics of the dataset on which the deep learning model is trained; moreover, it is manually determined based on the domain knowledge of an expert or selected from a grid search of possible candidates. Herein, we present a comparative study of different deep-learning-based sentiment classification model structures to derive meaningful implications for building sentiment classification models. Specifically, eight deep-learning models, three based on convolutional neural networks and five based on recurrent neural networks, with two types of input structures, i.e., word level and character level, are compared for 13 review datasets, and the classification performances are discussed under different perspectives.https://ieeexplore.ieee.org/document/8948030/Sentiment classificationdeep learningconvolutional neural networkrecurrent neural networkword embeddingcharacter embedding
spellingShingle Seungwan Seo
Czangyeob Kim
Haedong Kim
Kyounghyun Mo
Pilsung Kang
Comparative Study of Deep Learning-Based Sentiment Classification
IEEE Access
Sentiment classification
deep learning
convolutional neural network
recurrent neural network
word embedding
character embedding
title Comparative Study of Deep Learning-Based Sentiment Classification
title_full Comparative Study of Deep Learning-Based Sentiment Classification
title_fullStr Comparative Study of Deep Learning-Based Sentiment Classification
title_full_unstemmed Comparative Study of Deep Learning-Based Sentiment Classification
title_short Comparative Study of Deep Learning-Based Sentiment Classification
title_sort comparative study of deep learning based sentiment classification
topic Sentiment classification
deep learning
convolutional neural network
recurrent neural network
word embedding
character embedding
url https://ieeexplore.ieee.org/document/8948030/
work_keys_str_mv AT seungwanseo comparativestudyofdeeplearningbasedsentimentclassification
AT czangyeobkim comparativestudyofdeeplearningbasedsentimentclassification
AT haedongkim comparativestudyofdeeplearningbasedsentimentclassification
AT kyounghyunmo comparativestudyofdeeplearningbasedsentimentclassification
AT pilsungkang comparativestudyofdeeplearningbasedsentimentclassification