Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social Systems
Sentiment classification of online reviews is playing an increasingly important role for both consumers and businesses in cyber-physical-social systems. However, existing works ignore the semantic correlation among different reviews, causing the ineffectiveness for sentiment classification. In this...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8314135/ |
id |
doaj-dbc59b9261274c48bddc0fbfdfca86c3 |
---|---|
record_format |
Article |
spelling |
doaj-dbc59b9261274c48bddc0fbfdfca86c32021-03-29T21:00:09ZengIEEEIEEE Access2169-35362018-01-016179421795110.1109/ACCESS.2018.28134198314135Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social SystemsXu Yuan0Mingyang Sun1Zhikui Chen2https://orcid.org/0000-0002-9209-2189Jing Gao3Peng Li4School of Software, Dalian University of Technology, Dalian, ChinaSchool of Software, Dalian University of Technology, Dalian, ChinaSchool of Software, Dalian University of Technology, Dalian, ChinaSchool of Software, Dalian University of Technology, Dalian, ChinaSchool of Software, Dalian University of Technology, Dalian, ChinaSentiment classification of online reviews is playing an increasingly important role for both consumers and businesses in cyber-physical-social systems. However, existing works ignore the semantic correlation among different reviews, causing the ineffectiveness for sentiment classification. In this paper, a word embedding clustering-based deep hypergraph model (ECDHG) is proposed for the sentiment analysis of online reviews. The ECDHG introduces external knowledge by employing the pre-training word embeddings to express reviews. Then, semantic units are detected under the supervision of semantic cliques discovered by an improved hierarchical fast clustering algorithm. Convolutional neural networks are connected to extract the high-order textual and semantic features of reviews. Finally, the hypergraph can be constructed based on high-order relations of samples for the sentiment classification of reviews. Experiments are performed on five-domain data sets including movie, book, DVD, kitchen, and electronic to assess the performance of the proposed model compared with other seven models. The results validate that our model outperforms the compared methods in classification accuracy.https://ieeexplore.ieee.org/document/8314135/CNNshypergraphsentiment classificationonline reviewsshort text |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xu Yuan Mingyang Sun Zhikui Chen Jing Gao Peng Li |
spellingShingle |
Xu Yuan Mingyang Sun Zhikui Chen Jing Gao Peng Li Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social Systems IEEE Access CNNs hypergraph sentiment classification online reviews short text |
author_facet |
Xu Yuan Mingyang Sun Zhikui Chen Jing Gao Peng Li |
author_sort |
Xu Yuan |
title |
Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social Systems |
title_short |
Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social Systems |
title_full |
Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social Systems |
title_fullStr |
Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social Systems |
title_full_unstemmed |
Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social Systems |
title_sort |
semantic clustering-based deep hypergraph model for online reviews semantic classification in cyber-physical-social systems |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
Sentiment classification of online reviews is playing an increasingly important role for both consumers and businesses in cyber-physical-social systems. However, existing works ignore the semantic correlation among different reviews, causing the ineffectiveness for sentiment classification. In this paper, a word embedding clustering-based deep hypergraph model (ECDHG) is proposed for the sentiment analysis of online reviews. The ECDHG introduces external knowledge by employing the pre-training word embeddings to express reviews. Then, semantic units are detected under the supervision of semantic cliques discovered by an improved hierarchical fast clustering algorithm. Convolutional neural networks are connected to extract the high-order textual and semantic features of reviews. Finally, the hypergraph can be constructed based on high-order relations of samples for the sentiment classification of reviews. Experiments are performed on five-domain data sets including movie, book, DVD, kitchen, and electronic to assess the performance of the proposed model compared with other seven models. The results validate that our model outperforms the compared methods in classification accuracy. |
topic |
CNNs hypergraph sentiment classification online reviews short text |
url |
https://ieeexplore.ieee.org/document/8314135/ |
work_keys_str_mv |
AT xuyuan semanticclusteringbaseddeephypergraphmodelforonlinereviewssemanticclassificationincyberphysicalsocialsystems AT mingyangsun semanticclusteringbaseddeephypergraphmodelforonlinereviewssemanticclassificationincyberphysicalsocialsystems AT zhikuichen semanticclusteringbaseddeephypergraphmodelforonlinereviewssemanticclassificationincyberphysicalsocialsystems AT jinggao semanticclusteringbaseddeephypergraphmodelforonlinereviewssemanticclassificationincyberphysicalsocialsystems AT pengli semanticclusteringbaseddeephypergraphmodelforonlinereviewssemanticclassificationincyberphysicalsocialsystems |
_version_ |
1724193777780785152 |