Computer Science

Computer Science ›› 2026, Vol. 53 ›› Issue (4): 188-196.doi: 10.11896/jsjkx.250500088

• Database & Big Data & Data Science • Previous Articles     Next Articles

STWD-DLFRD:Multi-granularity Fake Review Detection via Sequential Three-way Decisions and Deep Learning

GU Bokai, LIU Dun, SUN Yang   

  1. School of Economics and Management, Southwest Jiaotong University, Chengdu 610031, China
  • Received:2025-05-22 Revised:2025-07-21 Online:2026-04-15 Published:2026-04-08
  • About author:GU Bokai,born in 2001,master,is a student member of CCF(No.Z6696G).His main research interests include data mining,fake reviews detection,three-way decision and granular computing.
    LIU Dun,born in 1983,Ph.D,professor,is a distinguished member of CCF(No.17413D).His main research in-terests include data mining and know-ledge discovery,rough set theory and granular computing,decision support systems.
  • Supported by:
    National Natural Science Foundation of China(62276217,62402424),Natural Science Foundation of Sichuan Province(2026NSFSC0445) and Fundamental Research Funds for the Central Universities(2682024KJ005,2682024ZTPY021).

PDF (PC)

53

Abstract: With the increasing influence of online reviews on consumer decision-making,fake review detection has become a critical task for maintaining the integrity of e-commerce ecosystems.Existing methods predominantly rely on static single-step detection,which overlooks dynamic feature evolution and cost-sensitive decision-making,leading to suboptimal efficiency.To address these limitations,this paper proposes a sequential three-way decisions and deep learning-based multi-granularity fake review detection framework(STWD-DLFRD).The framework constructs a multi-granularity feature space by extracting textual,behavioral and social relationship features from reviews.Leveraging a hierarchical decision mechanism of sequential three-way decisions,it dynamically identifies fake reviews with varying complexity levels.Experimental results demonstrate that STWD-DLFRD outperforms baseline models in both F1-score and accuracy,while significantly reducing total classification costs.This study provides an effective solution for high-cost-sensitive fake review detection in dynamic environments,balancing detection precision and decision efficiency through adaptive granularity refinement.

Key words: Fake review detection, Sequential three-way decisions, Deep learning, Multi-granularity features, Decision cost

CLC Number: 

  • TP183
[1]LI L Y,QIN B,LIU T.A Survey on Fake Review Detection[J].Chinese Journal of Computers,2018,41(4):946-968.
[2]ISTANTO R S H,MAHMUDY W F,BACHTIAR F A.Detection of online review spam:A literature review[C]//Proceedings of the 5th International Conference on Sustainable Information Engineering and Technology(SIET).New York:ACM,2020:57-63.
[3]LAI C L,XU K Q,LAU R Y K,et al.High-order concept associations mining and inferential language modeling for online review spam detection[C]//2010 IEEE International Conference on Data Mining Workshops.IEEE,2010:1120-1127.
[4]KUMAR A,GOPAL R D,SHANKAR R,et al.Fraudulent review detection model focusing on emotional expressions and explicit aspects:investigating the potential of feature engineering[J].Decision Support Systems,2022,155:113728.
[5]JABEUR S B,BALLOUK H,ARFI W B,et al.Artificial intelligence applications in fake review detection:Bibliometric analysis and future avenues for research[J].Journal of Business Research,2023,158:113631.
[6]CHIEN S Y,YANG C J,YU F.XFlag:Explainable fake news detection model on social media[J].International Journal of Human-Computer Interaction,2022,38(18/19/20):1808-1827.
[7]ZHANG J Y.Research on Feature Extraction and DetectionTechnology of Fake Reviews[J].Intelligent Computer and Applications,2023,13(10):52-55.
[8]WEI J R,WANG R T,WANG H.Large-scale Fake ReviewGroup Detection Based on Network Structure Features[J].Operations Research and Management Science,2023,32(1):194-200.
[9]SCHOENMÜLLER V,NETZER O,STAHL F.The extremedistribution of online reviews:Prevalence,drivers and implications[J].Journal of Marketing Research,2020,57(5):853-877..
[10]HAJEK P,SAHUT J M.Mining behavioural and sentiment-dependent linguistic patterns from restaurant reviews for fake review detection[J].Techonlogical Forecasting and Social Change,2022,177:121532.
[11]MUKHERJEE A,LIU B,GLANCE N.Spotting fake reviewer groups in consumer reviews[C]//Proceedings of the 21st International Conference on World Wide Web(WWW).New York:ACM,2012:191-200.
[12]XU C,ZHANG J,CHANG K,et al.Uncovering collusive spammers in Chinese review websites[C]//Proceedings of the 22nd ACM International Conference on Information and Knowledge Management(CIKM).New York:ACM,2013:979-988.
[13]WANG Z,WEI W,MAO X L,et al.User-based network embedding for opinion spammer detection[J].Pattern Recognition,2022,125:108512.
[14]PAUL H,NIKOLAEV A.Fake review detection on onlineE-commerce platforms:a systematic literature review[J].Data Mining and Knowledge Discovery,2021,35(5):1830-1881.
[15]SHANG Y,LIU M,ZHAO T,et al.T-Bert:A spam review detection model combining group intelligence and personalized sentiment information[C]//Proceedings of the International Conference on Artificial Neural Networks(ICANN).Cham:Sprin-ger,2021:409-421.
[16]BHUVANESHWARI P,RAO A N,ROBINSON Y H.Spam review detection using self attention based CNN and bi-directional LSTM[J].Multimedia Tools and Applications,2021,80(12):18107-18124.
[17]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(ICWSM).Palo Alto,CA:AAAI,2013:409-418.
[18]TANG X,QIAN T,YOU Z.Generating behavior features for cold-start spam review detection with adversarial learning[J].Information Sciences,2020,526:274-288.
[19]MANASKASEMSAK B,TANTISUWANKUL J,RUNGSA-WANG A.Fake review and reviewer detection throughbeha-vioral graph partitioning integrating deep neural network[J].Neural Computing and Applications,2023,35:1169-1182.
[20]CHENG L C,WU Y T,CHAO C T,et al.Detecting fake reviewers from the social context with a graph neural network method[J].Decision Support Systems,2024,179:114150.
[21]HE L,XU G,JAMEEL S,et al.Graph-aware deep fusion networks for online spam review detection[J].IEEE Transactions on Computational Social Systems,2022,10(5):2557-2565.
[22]LI A,QIN Z,LIU R,et al.Spam review detection with graph convolutional networks[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management(CIKM).New York:ACM,2019:2703-2711.
[23]DUMA R A,NIU Z,NYAMAWE A S,et al.A Deep Hybrid Model for fake review detection by jointly leveraging review text,overall ratings,and aspect ratings[J].Soft Computing,2023,27(10):6281-6296.
[24]ZHANG D,LI W,NIU B,et al.A deep learning approach for detecting fake reviewers:Exploiting reviewing behavior and textualinformation[J].Decision Support Systems,2023,166:113911.
[25]SAHOO S R,GUPTA B B.Classification of spammer and nonspammer content in online social network using genetic algorithm-based feature selection[J].Enterprise Information Systems,2020,14(5):710-736.
[26]YAO Y,DENG X.Sequential three-way decisions with probabilistic rough sets[C]//Proceedings of the 10th IEEE Internatio-nal Conference on Cognitive Informatics and Cognitive Computing.Piscataway,NJ:IEEE,2011:120-125.
[27]ZHANG G Q,LIU Q,JI L H.Multi-granularity Sentiment Classification Method Based on Sequential Three-way Decisions[J].Computer Science,2018,45(12):153-159.
[28]CHEN R,YANG X,LUO J F,et al.Research on SequentialThree-way Abnormal User Detection Based on GANs-LightGBM[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2021,33(5):816-825.
[29]LI H,ZHANG L,HUANG B,et al.Sequential three-way decision and granulation for cost-sensitive face recognition[J].Knowledge-Based Systems,2016,91:241-251.
[30]YAO Y Y,WONG S K M.A decision theoretic framework for approximatingconcepts[J].International Journal of Man-Machine Studies,1992,37(6):793-809.
[31]YANG X,LI Y,LI T.A review of sequential three-way decision and multi-granularity learning[J].International Journal of Approximate Reasoning,2023,152:414-433.
[32]LIU Y,AO X,QIN Z,et al.Pick and choose:A GNN-based imbalanced learning approach for fraud detection[C]//Proceedings of the Web Conference 2021(WWW).New York:ACM,2021:3168-3177.
[33]ZHANG G,LI Z,HUANG J,et al.eFraudCom:An e-commerce fraud detection system via competitive graph neural networks[J].ACM Transactions on Information Systems,2022,40(3):1-29.
[34]KHAN A,SOHAIL A,ZAHOORA U,et al.A survey of the recent architectures of deep convolutional neural networks[J].Artificial Intelligence Review,2020,53:5455-5516.
[35]ALSHARIF N.Fake opinion detection in an e-commerce business based on a long-short memory algorithm[J].Soft Computing,2022,26(16):7847-7854.
[36]JAVED M S,MAJEED H,MUJTABA H,et al.Fake reviews classification using deep learning ensemble of shallow convolutions[J].Journal of Computational Social Science,2021,4(2):883-902.
[37]OAK R.Detecting review fraud using metaheuristic graph neural networks[J].International Journal of Information Technology,2024,16(7):4019-4025.
[38]WANG J,WEN R,WU C,et al.FdGars:Fraudster detection via graph convolutional networks in online app review system[C]//Proceedings of the Companion of the 2019 World Wide Web Conference(WWW).New York:ACM,2019:310-316.
[39]REN Z,ZHANG X,ZHANG S,et al.Fake review detection via heterogeneous graph attention network[C]//Proceedings of the International Conference on Artificial Neural Networks(ICANN).Cham:Springer,2023:364-376.
[40]RAYANA S,AKOGLU L.Collective opinion spam detection:Bridging review networks and metadata[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(KDD).New York:ACM,2015:985-994.
[41]DOU Y,LIU Z,SUN L,et al.Enhancing graph neural network-based fraud detectors against camouflaged fraudsters[C]//Proceedings of the 29th ACM International Conference on Information and Knowledge Management(CIKM).New York:ACM,2020:315-324.
[42]ZHANG S,YIN H,CHEN T,et al.GCN-based user representation learning for unifying robust recommendation and fraudster detection[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:689-698.
[43]LIU D,YE X.A matrix factorization based dynamic granularity recommendation with three-way decisions[J].Knowledge-Based Systems,2020,191:105243.
[44]FAN Q,LIU D,YE X Q.Cost-sensitive Text Sentiment Analysis Based on Sequential Three-way Decision[J].Pattern Recognition and Artificial Intelligence,2020,33(8):732-742.
[1] ZHENG Cheng, BAN Qingqing. Knowledge-assisted and Reinforced Syntax-driven for Aspect-based Sentiment Analysis [J]. Computer Science, 2026, 53(4): 406-414.
[2] YIN Chuang, LIU Jianyi, ZHANG Ru. Cross-modal Fusion Few-sample Ransomware Classifier:Multimodal Encoding Based on Pre-trained Models [J]. Computer Science, 2026, 53(4): 435-444.
[3] GAO Tai, REN Yanzhang, WANG Huiqing, LI Ying, WANG Bin. KGMamba:Gene Regulatory Network Prediction Model Based on Kolmogorov-Arnold Network Optimizing Graph Convolutional Network and Mamba [J]. Computer Science, 2026, 53(4): 101-111.
[4] ZHANG Xueqin, WANG Zhineng, LI Jinsheng, LU Yisong, LUO Fei. Key Node Identification in Temporal Social Networks Based on Deep Learning and Multi-feature Fusion [J]. Computer Science, 2026, 53(4): 143-154.
[5] LI Zequn, DING Fei. Fatigue Driving Detection Based on Dual-branch Fusion and Segmented Domain AdaptationTransfer Learning [J]. Computer Science, 2026, 53(3): 78-87.
[6] FU Yukai, LI Qingzhen, DONG Zhixue, SHI Dongli, ZHAO Peng. Pedestrian Re-identification Methods Based on Limited Target Data and Deep Learning [J]. Computer Science, 2026, 53(3): 287-294.
[7] YU Ding, LI Zhangwei. Prediction Method of RNA Secondary Structure Based on Transformer Architecture [J]. Computer Science, 2026, 53(3): 375-382.
[8] DU Jiantong, GUAN Zeli, XUE Zhe. Multi-task Learning-based Ophthalmic Video Feature Fusion and Multi-dimensional Profiling [J]. Computer Science, 2026, 53(3): 383-391.
[9] SU Ruitao, REN Jiongjiong, CHEN Shaozhen. Deep Learning-based Neural Differential Distinguishers for GIFT-128 and ASCON [J]. Computer Science, 2026, 53(3): 453-458.
[10] HUANG Jing, WANG Teng, LIU Jian, HU Kai, PENG Xin, HUANG Yamin, WEN Yuanqiao. Multimodal Visual Detection for Underwater Sonar Target Images [J]. Computer Science, 2026, 53(2): 227-235.
[11] LIU Chenhong, LI Fenglian, YANG Jia, WANG Suzhe, CHEN Guijun. Boundary-focused Multi-scale Feature Fusion Network for Stroke Lesion Segmentation [J]. Computer Science, 2026, 53(2): 264-272.
[12] XI Penghui, WU Xiazhen, JIANG Wencong, FANG Liangda, HE Chaobo, GUAN Quanlong. Review of Personalized Educational Resource Recommendations [J]. Computer Science, 2026, 53(2): 1-15.
[13] HUANG Miaomiao, WANG Huiying, WANG Meixia, WANG Yejiang , ZHAO Yuhai. Review of Graph Embedding Learning Research:From Simple Graph to Complex Graph [J]. Computer Science, 2026, 53(1): 58-76.
[14] WANG Cheng, JIN Cheng. KAN-based Unsupervised Multivariate Time Series Anomaly Detection Network [J]. Computer Science, 2026, 53(1): 89-96.
[15] XUE Jingyan, XIA Jianan, HUO Ruili, LIU Jie, ZHOU Xuezhong. Review of Retinal Image Analysis Methods for OCT/OCTA Based on Deep Learning [J]. Computer Science, 2026, 53(1): 128-140.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.