File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A deceptive review detection framework: Combination of coarse and fine-grained features

TitleA deceptive review detection framework: Combination of coarse and fine-grained features
Authors
KeywordsDeceptive reviews detection
LDA topic model
Deep learning
Coarse-grained features
Fine-grained features
Issue Date2020
PublisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/eswa
Citation
Expert Systems with Applications, 2020, v. 156, p. article no. 113465 How to Cite?
AbstractElectronic commerce has become a popular shopping mode. To enhance their reputations, attract more customers, and finally obtain more benefits, dishonest sellers often recruit buyers or robots to post a large number of deceptive reviews to mislead users. According to the interpretability of learning results, existing methods for detecting deceptive reviews can be mainly divided into explicit feature-based mining ones and neural network-based implicit feature mining ones. The nature of these works is accurate text classification based on coarse-grained features (e.g., topic, sentence, and document) or fine-grained features (e.g., word). To take full merits of existing approaches, this paper proposes a new framework that explores a method to combine the coarse-grained features and the fine-grained features. In this framework, the coarse-grained implicit semantic features of the topic distribution are learned by the concatenation of a Latent Dirichlet Allocation (LDA) topic model and a 2-layered neural network. The fine-grained implicit semantic features from the word vectors representation of the reviews are parallelly learned by a deep learning framework. Finally, these two granular features are combined and adopted to train a Support Vector Machine (SVM) classifier for detecting whether a review is deceptive or not. To verify the effectiveness and performance of this framework, we derive three models by specifying three popular deep learning models, such as TextCNN, long short-term memory (LSTM), and Bi-directional LSTM (BiLSTM) to learn the fine-grained features. Experimental results on a mixed-domain dataset and balanced/unbalanced in-domain datasets show that all the combination models are superior to the corresponding baseline models considering single features.
Persistent Identifierhttp://hdl.handle.net/10722/286373
ISSN
2023 Impact Factor: 7.5
2023 SCImago Journal Rankings: 1.875
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorCao, N-
dc.contributor.authorJI, S-
dc.contributor.authorChiu, DKW-
dc.contributor.authorHe, M-
dc.contributor.authorSun, X-
dc.date.accessioned2020-08-31T07:02:56Z-
dc.date.available2020-08-31T07:02:56Z-
dc.date.issued2020-
dc.identifier.citationExpert Systems with Applications, 2020, v. 156, p. article no. 113465-
dc.identifier.issn0957-4174-
dc.identifier.urihttp://hdl.handle.net/10722/286373-
dc.description.abstractElectronic commerce has become a popular shopping mode. To enhance their reputations, attract more customers, and finally obtain more benefits, dishonest sellers often recruit buyers or robots to post a large number of deceptive reviews to mislead users. According to the interpretability of learning results, existing methods for detecting deceptive reviews can be mainly divided into explicit feature-based mining ones and neural network-based implicit feature mining ones. The nature of these works is accurate text classification based on coarse-grained features (e.g., topic, sentence, and document) or fine-grained features (e.g., word). To take full merits of existing approaches, this paper proposes a new framework that explores a method to combine the coarse-grained features and the fine-grained features. In this framework, the coarse-grained implicit semantic features of the topic distribution are learned by the concatenation of a Latent Dirichlet Allocation (LDA) topic model and a 2-layered neural network. The fine-grained implicit semantic features from the word vectors representation of the reviews are parallelly learned by a deep learning framework. Finally, these two granular features are combined and adopted to train a Support Vector Machine (SVM) classifier for detecting whether a review is deceptive or not. To verify the effectiveness and performance of this framework, we derive three models by specifying three popular deep learning models, such as TextCNN, long short-term memory (LSTM), and Bi-directional LSTM (BiLSTM) to learn the fine-grained features. Experimental results on a mixed-domain dataset and balanced/unbalanced in-domain datasets show that all the combination models are superior to the corresponding baseline models considering single features.-
dc.languageeng-
dc.publisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/eswa-
dc.relation.ispartofExpert Systems with Applications-
dc.subjectDeceptive reviews detection-
dc.subjectLDA topic model-
dc.subjectDeep learning-
dc.subjectCoarse-grained features-
dc.subjectFine-grained features-
dc.titleA deceptive review detection framework: Combination of coarse and fine-grained features-
dc.typeArticle-
dc.identifier.emailChiu, DKW: dchiu88@hku.hk-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.eswa.2020.113465-
dc.identifier.scopuseid_2-s2.0-85084923756-
dc.identifier.hkuros313596-
dc.identifier.volume156-
dc.identifier.spagearticle no. 113465-
dc.identifier.epagearticle no. 113465-
dc.identifier.isiWOS:000542130000009-
dc.publisher.placeUnited Kingdom-
dc.identifier.issnl0957-4174-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats