A deceptive detection model based on topic, sentiment, and sentence structure information

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 50; no. 11; pp. 3868 - 3881
• Main Authors: Du, Xiaodong, Zhu, Ruiqi, Zhao, Fuqiang, Zhao, Fangzhou, Han, Ping, Zhu, Zhengyu
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2020; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Classification; Computer Science; Deception; Dirichlet problem; Feature extraction; Linguistics; Machines; Manufacturing; Maximum likelihood estimates; Mechanical Engineering; Methods; Probability distribution; Processes; Support vector machines; Multiple-classifier; Feature extraction; Deceptive detection; Topic model
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-020-01779-0

Deceptive reviews on Web are a common phenomenon and how to detect them has a very important impact on products, services, and even business policies. In order to filter out deceptive reviews more accurately, a new model called Sentence Joint Topic Sentiment Model (SJTSM) is presented in this paper, which incorporates the sentence structure of reviews and the sentiment label information of words based on Latent Dirichlet Allocation (LDA) model to extract the review features. The proposed model employs Gibbs algorithm to estimate the maximum likelihood parameters and takes the vector of topic-sentiment distribution as the review features. Then a voting system of multiple-classifier, which takes the extracted review feature vector as its input is designed to realize the classification of deceptive review detection. The comparative experiments on different public datasets with other existing methods based on LDA model show that the new classifying system based on SJTSM model can achieve more satisfying classification results on deceptive review detection.