ABSTRACT
Deep learning neural networks have significantly improved the detection rate of false comments, but their processing of text is still serializable, and there are still shortcomings in addressing the implicit connections between false comments. Therefore, a false comment detection model based on CNN GRU is proposed. For this model, first analyze the characteristics of false comments in real websites, preprocess the dataset, and then use Doc2vec to extract word vectors from the text, so that the input data can be combined with contextual context and preserve word order information. Then, CNN is used for text feature representation, GRU is introduced for comment classification, and the final CNN GRU model is constructed. By comparing the performance of models with different parameters in false comment detection through experiments, the most suitable model structural parameters are obtained. Finally, a performance comparison was conducted with commonly used machine learning algorithms and neural network models to verify the effectiveness of the CNN-GRU model.
- G. S. Budhi, R. Chiong, I. Pranata and Z. Hu, "Predicting rating polarity through automatic classification of review texts," 2017 IEEE Conference on Big Data and Analytics (ICBDA), Kuching, Malaysia, 2017, pp. 19-24, doi: 0.1109/ICBDAA.2017.8284101.Google Scholar
- Wen Song, Wenli Li, Shidao Geng, Effect of online product reviews on third parties'selling on retail platforms, Electronic Commerce Research and Applications, Volume 39, 2020, 100900, ISSN 1567-4223,https://doi.org/10.1016/j.elerap.2019.100900.Google ScholarDigital Library
- Felbermayr A, Nanopoulos A. The Role of Emotions for the Perceived Usefulness in Online Customer Reviews [J]. Journal of Interactive Marketing, 2016, 36(nov.):60-76.DOI:10.1016/j.intmar.2016.05.004.Google ScholarCross Ref
- Gossling S, Hall C M, Andersson A C. The manager's dilemma: a conceptualization of online review manipulation strategies[J]. Current Issues in Tourism, 2018, 21(1): 484-503.DOI:10.1080/13683500.2015.1127337.Google ScholarCross Ref
- Bolton R J, Hand D J. Statistical fraud detection: A review[J]. Operations Research, 2004, 17(3): 235–255.Google Scholar
- Yi,Zhao, Sha, Modeling Consumer Learning from Online Product Reviews [J].Marketing Science, 2013. DOI:10.1287/mksc.1120.0755.Google ScholarDigital Library
- Zhang W , Xie R , Wang Q ,et al. A novel approach for fraudulent reviewer detection based on weighted topic modelling and nearest neighbors with asymmetric Kullback–Leibler divergence[J].Decision Support Systems, Volume 157, 2022, 113765, ISSN 0167-9236,https://doi.org/10.1016/j.dss.2022.113765.Google ScholarCross Ref
- Tian Y , Mirzabagheri M , Tirandazi P ,et al.A non-convex semi-supervised approach to opinion spam detection by ramp-one class SVM[J].Information Processing & Management, 2020, 57(6):102381.DOI:10.1016/j.ipm.2020.102381.Google ScholarCross Ref
- Elmogy A M , Tariq U , Mohammed A ,et al. Fake Reviews Detection using Supervised Machine Learning [J].International Journal of Advanced Computer Science and Applications, 36(1): 601-606, 2021. DOI:10.14569/IJACSA.2021.0120169.Google ScholarCross Ref
- Wang Zhuo, Wang Hao, Hu Run-long, Store Fake Review Detection Based on Supervised Learning[J]. Software Guide, 2020, 19(04): 71-74. DOI:10.11907/rjdk.191695.Google ScholarCross Ref
- Kontsewaya Y , Antonov E , Artamonov A A .Evaluating the Effectiveness of Machine Learning Methods for Spam Detection[J].Procedia Computer Science, 2021, 190(2): 479-486.DOI:10.1016/J.PROCS.2021.06.056.Google ScholarDigital Library
- Dong Zhang, Wenwen Li, Baozhuang Niu, Chong Wu, A deep learning approach for detecting fake reviewers: Exploiting reviewing behavior and textual information, Decision Support Systems, Volume 166, 2023, 113911, ISSN 0167-9236, https://doi.org/10.1016/j.dss.2022.113911.Google ScholarDigital Library
- Hlee S , Lee H , Koo C ,et al. Exploring the relationship between time trend and online restaurant reviews [J].Telematics and Informatics, 2021, 59(2): 101560.DOI:10.1016/j.tele.2020.101560.Google ScholarCross Ref
- Sastrawan I K , Bayupati I P A , Arsa D M S . Detection of fake news using deep learning CNN-RNN based methods [J]. ICT Express, 2022, 8(3): 396-408.Google ScholarCross Ref
- Goldani M H , Safabakhsh R , Momtazi S .Convolutional neural network with margin loss for fake news detection [J].Information Processing & Management, 58( 1), 2023, 09, 28. DOI:10.1016/j.ipm.2020.102418.Google ScholarCross Ref
- Ruan N , Deng R , Su C .GADM: Manual fake review detection for O2O commercial platforms[J].Computers & Security, 2020, 88(Jan.):101657.1-101657.11.DOI:10.1016/j.cose.2019.101657.Google ScholarDigital Library
- Wanda P , Jie H J .DeepProfile: Finding fake profile in online social network using dynamic CNN[J].Journal of Information Security and Applications, 2020, 52:102465.DOI:10.1016/j.jisa.2020.102465.Google ScholarCross Ref
- Bathla G , Singh P , Singh R ,et al. Intelligent fake reviews detection based on aspect extraction and analysis using deep learning[J].Neural Computing and Applications, 2022, 34:20213 - 20229.DOI:10.1007/s00521-022-07531-8.Google ScholarDigital Library
- CHEN Yu-feng. False Comment Detection Using CNN-LSTM and Transfer Learning [J]. Software Guide, 2022, 21(02): 63-67.Google Scholar
- Jiangtao Qiu, Siyu Wang, A deep matching model for detecting reviews mismatched with products in e-commerce,Applied Soft Computing, Volume 129, 2022, 109624,ISSN 1568-4946,https://doi.org/10.1016/j.asoc.2022.109624.Google ScholarDigital Library
- Simran Bajaj, Niharika Garg, Sandeep Kumar Singh. A Novel User-based Spam Review Detection[J].Procedia Computer Science, 2017, 122: 1009-1015.DOI:10.1016/j.procs.2017.11.467.Google ScholarCross Ref
- Rastogi A , Mehrotra M , Ali S S .Effective Opinion Spam Detection: A Study on Review Metadata Versus Content[J].Journal of Data and Information Science, 2020, 5(2): 76-110.DOI:CNKI:SUN:WXQB.0.2020-02-005.Google ScholarCross Ref
- Martens, D., Maalej, W. Towards understanding and detecting fake reviews in app stores. Empir Software Eng 24, 3316–3355, 2019. https://doi.org/10.1007/s10664-019-09706-9.Google ScholarCross Ref
- Akram A U , Khan H U , Iqbal S ,et al. Finding Rotten Eggs: A Review Spam Detection Model using Diverse Feature Sets [J]. KSII Transactions on Internet and Information Systems, 2018, 12(10):5120-5142.DOI:10.3837/tiis.2018.10.026.Google ScholarCross Ref
- Mukherjee A , Venkataraman V , Liu B ,et al.What yelp fake review filter might be doing? [C]. Proceedings of the International AAAI Conference on Web and Social Media, 2013, 7(1): 409-418.DOI:6006.Google ScholarCross Ref
- Sun, Chengai, Qiaolin, Exploiting Product Related Review Features for Fake Review Detection.[J].Mathematical Problems in Engineering, 2016, 2016(1):1-7.DOI:10.1155/2016/4935792.Google ScholarCross Ref
- Jindal N, Liu B. Analyzing and detecting review spam[C]. Seventh IEEE international conference on data mining, 2007: 547-552. DOI:10.1109/TKDE.2016.2607202.Google ScholarDigital Library
- Mikolov T, Sutskever, I, Chen, K, Distributed representations of words and phrases and their compositionality[c]. 27th Annual Conference on Neural Information Processing Systems, NIPS 2013, December 5, 2013 - December 10, 2013, Lake Tahoe, NV, United states.Google Scholar
Index Terms
- Research on False Comment Detection Model Based on the Fusion of Convolutional Neural Network and GRU
Recommendations
Network intrusion detection using fusion features and convolutional bidirectional recurrent neural network
In this paper, novel fusion features to train Convolutional Bidirectional Recurrent Neural Network (CBRNN) are proposed for network intrusion detection. UNSW-NB15 data sets' attack behaviours (input features) are fused with their first and second-order ...
Sentiment strength detection with a context-dependent lexicon-based convolutional neural network
AbstractSentiment 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 ...
New GRU from convolutional neural network and gated recurrent unit
DATA '18: Proceedings of the First International Conference on Data Science, E-learning and Information SystemsThis paper describes our comparison between two deep learning systems. Initially we start with the first system which is used Convolutional Neural Network CNN which we will compare with the second system which is used Gated Recurrent Unit GRU. And ...
Comments