Document Type : Original/Review Paper

Authors

1 Faculty of New Sciences and Technology, University of Tehran, Tehran, Iran.

2 School of Computer Science, Institute for Research in Fundamental Science (IPM), Tehran, Iran.

3 Department of Computer Engineering, Yazd University, Yazd, Iran.

4 Department of Electrical, Electronic, and Computer Engineering, University of Western Australia, Perth, Australia.

Abstract

Nowadays, some e-advice websites and social media like e-commerce businesses, provide not only their goods but a new way that their customers can give their opinions about products. Meanwhile, there are some review spammers who try to promote or demote some specific products by writing fraud reviews. There have been several types of researches and studies toward detecting these review spammers, but most studies are based on individual review spammers and few of them studied group review spammers, nevertheless it should be mentioned that review spammers can increase their effects by cooperating and working together. More words, there have been many features introduced in order to detect review spammers and it is better to use the efficient ones. In this paper we propose a novel framework, named Network Based Group Review Spammers which tries to identify and classify group review spammers with the usage of the heterogeneous information network. In addition to eight basic features for detecting group review spammers, three efficient new features from previous studies were modified and added in order to improve detecting group review spammers. Then with the definition of Meta-path, features are ranked. Results showed that by using the importance of features and adding three new features in the suggested framework, group review spammers detection is improved on Amazon dataset.

Keywords

[1] M. Hu, G. Xu, C. Ma., and M. Daneshmand, "Detecting review spammer groups in dynamic review networks", In Proceedings of the ACM Turing Celebration Conference-China, 2019.
 
[2] Y. Ren,  D. Ji., "Learning to Detect Deceptive Opinion Spam: A Survey", IEEE Access 7, pp. 42934-42945, 2019.
 
[3] F. Gillani, E. Al-Shaer, and B. AsSadhan, "Economic metric to improve spam detectors", Journal of Network and Computer Applications, 65, pp. 131-143, 2016.
 
[4] H. Li, Z. Chen, B. Liu, X. Wei, and J. Shao, "Spotting Fake Reviews via Collective Positive-Unlabeled Learning", In International Conference on Data Mining, IEEE,  pp. 894-904, 2014.
[5] A. Mukherjee, V. Venkataraman, B. Liu, and N. Glance, "What Yelp Fake Review Filter Might be Doing?", In 17th International AAAI Conference on Weblogs and Social Media, pp. 1-10, 2013.
 
[6] R. Kaur, S. Singh, and H. Kumar, "Rise of spam and compromised accounts in online social networks: A state-of-the-art review of different combating approaches", Journal of Network and Computer Applications, 112, pp. 53-88, 2018.
 
[7] A. Mukherjee, A. Kumar, B. Liu, J. Wang, M. Hsu, and M. Castellanos, "Spotting Opinion Spammers using Behavioral Footprints", In 19th SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, pp. 632-640, 2013.
 
[8] B. Viswanath, M. A. Bashir, and M. C. Guha, "Towards Detecting Anomalous User Behavior in Online Social Networks", In 23rd USENIX Security Symposium,  pp. 223-238, 2014.
 
[9] J. Fu, P. Lin, and S. Lee, "Detecting spamming activities in a campus network using incremental learning", Journal of Network and Computer Applications, 43 , pp. 56-65, 2014.
 
[10] A. Ala’M., J. Alqatawna, H. Faris, and M. A. Hassonah. "Spam profiles detection on social networks using computational intelligence methods: the effect of the lingual context." Journal of Information Science 47, No. 1 (2021): 58-81.
 
[11] C. Chen, H. Zhao, and Y. Yang, "Deceptive Opinion Spam Detection using Deep Level Linguistic Features", In National CCF Conference on Natural Language Processing and Chinese Computing, pp. 465-474, 2015.
 
[12] R. Ghai, S. Kumar, and A. C. Pandey, "Spam Detection using Rating and Review Processing Method", In Smart Innovations in Communication and Computational Sciences. Springer, Singapore, pp. 189-198, 2019.
 
[13] P. P. Chan, C. Yang, D. S. Yeung, and W. W. Ng, "Spam filtering for short messages in adversarial environment",  Neurocomputing, 155, pp. 167-176, 2015.
 
[14] A. Zulfikar, B. Carminati, and E. Ferrari. "A deep learning model for Twitter spam detection." Online Social Networks and Media 18 (2020): 100079.
 
[15] E. Elakkiya, S. Selvakumar, and RL. Velusamy. "TextSpamDetector: textual content-based deep learning framework for social spam detection using conjoint attention mechanism." Journal of Ambient Intelligence and Humanized Computing (2020): 1-16.
 
[16] M. Ghanbari, M. Salehi, and V. Ranjbar: Anomaly Detection in Heterogeneous Information Networks. in Proc. Second National Informatics Conference of Iran, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran, 23-24 December 2020. (Persian).
 
[17] Shaghayegh Najari, Mostafa Salehi, and Reza Farahbakhsh: GANBOT: A GAN-based Framework for Social Bot Detection, 2021.
 
[18] A.    D. Manqing, L. Yao, X. Wang, B. Benatallah, Ch. Huang, and X. Ning. "Opinion fraud detection via neural auto-encoder decision forest." Pattern Recognition Letters 132 (2020): 21-29.
 
[19] L. Akoglu, H. Tong, and D. Koutra, "Graph-based anomaly detection and description: a survey", In 21th International Conference on Information and Knowledge Management, ACM, pp. 626-689, 2015.
[20] S. Rayana and L. Akoglu, "Collective Opinion Spam Detection: Bridging Review Networks and Metadata", In 21st SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, pp. 985-994, 2015.
 
[21] K. Henderson, B. Gallagher, L. Li, and L. Akoglu, "It is Who You Know: Graph Mining using Recursive Structural Features", In 17th SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, pp. 663-671, 2011.
 
[22] R. S. Wu, C. Ou, H. Y. Lin, S. I. Chang, and D. C. Yen, “Using a data mining technique to enhance tax evasion detection performance”, Expert Systems with Applications. 39(10), pp. 8769-8777, 2011.
 
[23] H. Li, A. Mukherjee, B. Liu, R. Kornfieldz, and S. Emeryz, "Detecting Campaign Promoters on Twitter using Markov Random Field", In International Conference on Data Mining, IEEE, pp. 290-299, 2015.
 
[24] Q. Meng, S. Tafavogh, and P. Kennedy, "Community Detection on Heterogeneous Networks by Multiple Semantic-Path Clustering", In 6th International Conference on Computational Aspects of Social Networks, IEEE,  pp. 7-12, 2014.
 
[25] Z. Wang, T. Hou, D. Song, Z. Li, and T. Kong, "Detecting Review Spammer groups via Bipartite Graph Projection", The Computer Journal, 59(6), pp.861-874, 2017.
 
[26] A.    N, Shirin, Nb. Salim, and N. Hawaniah Zakaria. "Opinion spam detection: using multi-iterative graph-based model." Information Processing and Management 57, No. 1 (2020): 102140.
 
[27] A. Hashemi and Z. Chahooki, "GroupRank: Ranking Online Social Groups Based on User Membership Records." Journal of AI and Data Mining 9, no. 1 : 45-57 (2021).
 
[28] Yanhong Li, Gang Kou, Guangxu Li, and Haomin Wang: Multi-attribute group decision making with opinion dynamics based on social trust network. Information Fusion 75: 102-115 (2021).
 
[29] Pasquale De Meo, Emilio Ferrara, Domenico Rosaci, and Giuseppe M. L. Sarnè: Trust and Compactness in Social Network Groups. IEEE Transactions on Cybernetics 45(2): 205-216 (2015).
 
[30] S. Cresci, R. D. Pietro, M. Petrocchi, A. Spognardi, and M. Tesconi, "The paradigm-shift of social spambots: evidence, theories, and tools for the arms race", In Proceedings of the 26th International Conference on World Wide Web Companion, pp. 963-972, 2017.
 
[31] E. Choo, T. Yu, and M. Chi, "Detecting Opinion Spammer Groups through Community Discovery and Sentiment Analysis", In International Federation for Information Processing, pp.170-188, 2015.
 
[32] C, Chao, Y. Wang, J. Zhang, Y. Xiang, W. Zhou, and G. Min, "Statistical features-based real-time detection of drifted Twitter spam",  IEEE Transactions on Information Forensics and Security 12, No. 4, pp. 914-925, 2017.
 
[33] N. Aloshban and N. Aloshban, "A new approach for group spam detection in social media for Arabic language", In 8th International Conference on Latest Trends in Engineering and Technology, pp.130-137, 2016.
 
[34] G. Xu, M. Hu, C. Ma, and M. Daneshmand, "GSCPM: CPM-based Group Spamming Detection in Online Product Reviews", In IEEE International Conference on Communications (ICC), pp. 1-6, 2019.
 
[35] K. S. Adewole, N. B. Anuar, A. Kamsin, K. D. Varathan, and S. B. Razak, "Malicious accounts: dark of the social networks", Journal of Network and Computer Applications 79, pp. 41-67, 2017.
 
[36] S. Shehnepoor, M. Salehi, R. Farahbakhsh, and N. Crespi, "NetSpam: a Network-based Spam Detection Framework for Reviews in Online Social Media", Transactions on Information Forensics and Security, IEEE. 12(7), pp.1585-1595, 2017.
 
[37] B. Manaskasemsak, C. Chanmakho, J. Klainongsuang, and A. Rungsawang,  "Opinion Spam Detection through User Behavioral Graph Partitioning Approach", Proceedings of the 3rd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence, ACM, pp. 73-77, 2019.
 
[38] Y. Chao, R. Harkreader, and G. Gu, "Empirical evaluation and a new design for fighting evolving twitter spammers", IEEE Transactions on Information Forensics and Security 8, No. 8, pp. 1280-1293, 2018.
 
[39] C, Chao, Y. Wang, J. Zhang, Y. Xiang, W. Zhou, and G. Min, "Statistical features-based real-time detection of drifted Twitter spam",  IEEE Transactions on Information Forensics and Security 12, No. 4, pp. 914-925, 2017.
 
[40] M. Fazil and M. Abulaish, "A Hybrid Approach for Detecting Automated Spammers in Twitter", IEEE Transactions on Information Forensics and Security, 2018.
 
[41] Z. Chensu, Y. Xin, X. Li, Y. Yang, and Y. Chen. "A heterogeneous ensemble learning framework for spam detection in social networks with imbalanced data." Applied Sciences 10, No. 3 936. (2020).
 
[42] R. Agrawal and R. Srikant, “Fastalgorithms for mining associationrules”, VLDB, 1994.