{"type":"ScholarlyArticle","title":"Spotting Collective Behaviour of Online Frauds in Customer Reviews","authors":[{"name":"Sarthika Dhawan","slug":"sarthika-dhawan","given":"Sarthika","family":"Dhawan","affiliation":"Indraprastha Institute of Information Technology Delhi (IIITD) , India"},{"name":"Siva Charan Reddy Gangireddy","slug":"siva-charan-reddy-gangireddy","given":"Siva Charan Reddy","family":"Gangireddy","affiliation":"Indraprastha Institute of Information Technology Delhi (IIITD) , India"},{"name":"Shiv Kumar","slug":"shiv-kumar","given":"Shiv","family":"Kumar","affiliation":"Netaji Subhas University of Technology (NSUT) , Delhi , India"},{"name":"Tanmoy Chakraborty","slug":"tanmoy-chakraborty","given":"Tanmoy","family":"Chakraborty","affiliation":"Indraprastha Institute of Information Technology Delhi (IIITD) , India"}],"abstract":"Online reviews play a crucial role in deciding the quality before purchasing any product. Unfortunately, spammers often take advantage of online review forums by writing fraud reviews to promote/demote certain products. It may turn out to be more detrimental when such spammers collude and collectively inject spam reviews as they can take complete control of users' sentiment due to the volume of fraud reviews they inject.  Group spam detection is thus more challenging than individual-level fraud detection due to unclear definition of a group, variation of inter-group  dynamics, scarcity of labeled group-level spam data, etc. Here, we propose DeFrauder, an unsupervised method to detect online fraud reviewer groups. It first detects candidate fraud groups by leveraging the underlying product review graph and incorporating several behavioral signals which model multi-faceted collaboration among reviewers. It then maps reviewers into an embedding space and assigns a spam score to each group such that groups comprising spammers with highly similar behavioral traits achieve high spam score. While comparing with five baselines on four real-world datasets (two of them were curated by us), DeFrauder shows superior performance by outperforming the best baseline with 17.11% higher NDCG@50 (on average) across datasets.","doi":"10.24963/ijcai.2019/35","url":"https://ijcai.org/proceedings/2019/35","pdf":"https://ijcai.org/proceedings/2019/0035.pdf","markdown":"https://ijcai.org/proceedings/2019/35.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/35","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Agent-based and Multi-agent Systems","track":"Main track","number":35,"pages":{"first":245,"last":251},"keywords":["Agent-based and Multi-agent Systems: Trust and Reputation","Multidisciplinary Topics and Applications: Security and Privacy"],"videos":[],"references":[{"position":1,"raw":"[Akoglu et al., 2013] Leman Akoglu, Rishi Chandy, and Christos Faloutsos. Opinion fraud detection in online re- views by network effects. In ICWSM, pages 985--994, 2013.","title":"Opinion fraud detection in online reviews by network effects","authors":"Leman Akoglu, Rishi Chandy, Christos Faloutsos","year":"2013","venue":"ICWSM","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Allahbakhsh et al., 2013] Mohammad Allahbakhsh, Alek- sandar Ignjatovic, Boualem Benatallah, Elisa Bertino, Norman Foo, et al. Collusion detection in online rating systems. In Asia-Pacific Web Conference, pages 196-207. Springer, 2013.","title":"Collusion detection in online rating systems","authors":"Mohammad Allahbakhsh, Aleksandar Ignjatovic, Boualem Benatallah, Elisa Bertino, Norman Foo","year":"2013","venue":"Asia-Pacific Web Conference","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chetan et al., 2019] Aditya Chetan, Brihi Joshi, Hri- doy Sankar Dutta, and Tanmoy Chakraborty. Corerank: Ranking to detect users involved in blackmarket-based collusive retweeting activities. In WSDM, pages 330-338, 2019.","title":"Corerank: Ranking to detect users involved in blackmarket-based collusive retweeting activities","authors":"Aditya Chetan, Brihi Joshi, Hridoy Sankar Dutta, Tanmoy Chakraborty","year":"2019","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dhawan et al., 2019] Sarthika Dhawan, Siva Charan Reddy Gangireddy, Shiv Kumar, and Tanmoy Chakraborty. Defrauder: Supplementary. https://github.com/LCS2- IIITD/DeFrauder, 2019.","title":"Sarthika Dhawan","authors":"Dhawan","year":"2019","venue":null,"doi":null,"url":"https://github.com/LCS2-IIITD/DeFrauder,2019","internal_url":null},{"position":5,"raw":"[Dutta et al., 2018] Hridoy Sankar Dutta, Aditya Chetan, Brihi Joshi, and Tanmoy Chakraborty. Retweet us, we will retweet you: Spotting collusive retweeters involved in blackmarket services. In ASONAM, pages 242-249, 2018.","title":"Retweet us, we will retweet you: Spotting collusive retweeters involved in blackmarket services","authors":"Aditya Hridoy Sankar Dutta, Brihi Chetan, Tanmoy Joshi, Chakraborty","year":"2018","venue":"ASONAM","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fei et al., 2013] Geli Fei, Arjun Mukherjee, Bing Liu, Me- ichun Hsu, Malu Castellanos, and Riddhiman Ghosh. Ex- ploiting burstiness in reviews for review spammer detec- tion. In ICWSM, 2013.","title":"Exploiting burstiness in reviews for review spammer detection","authors":"Geli Fei, Arjun Mukherjee, Bing Liu, Meichun Hsu, Malu Castellanos, Riddhiman Ghosh","year":"2013","venue":"ICWSM","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Grover and Leskovec, 2016] Aditya Grover and Jure Leskovec. Node2vec: Scalable feature learning for networks. In SIGKDD, pages 855-864, 2016.","title":"Node2vec: Scalable feature learning for networks","authors":"Leskovec Grover, Aditya Grover, Jure Leskovec","year":"2016","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He and McAuley, 2016] Ruining He and Julian McAuley. Ups and downs: Modeling the visual evolution of fash- ion trends with one-class collaborative filtering. In WWW, pages 507-517, 2016.","title":"Ruining He and Julian McAuley. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering","authors":"Mcauley He","year":"2016","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kou et al., 2004] Yufeng Kou, Chang-Tien Lu, Sirirat Sir- wongwattana, and Yo-Ping Huang. Survey of fraud detec- tion techniques. In ICNSC, pages 749-754, 2004.","title":"Survey of fraud detection techniques","authors":"Yufeng Kou, Chang-Tien Lu, Sirirat Sirwongwattana, Yo-Ping Huang","year":"2004","venue":"ICNSC","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lim et al., 2010] Ee-Peng Lim, Viet-An Nguyen, Nitin Jin- dal, Bing Liu, and Hady Wirawan Lauw. Detecting prod- uct review spammers using rating behaviors. In CIKM, pages 939-948. ACM, 2010.","title":"Detecting product review spammers using rating behaviors","authors":"Ee-Peng Lim, Viet-An Nguyen, Nitin Jindal, Bing Liu, Hady Wirawan Lauw","year":"2010","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Manning et al., 2010] Christopher Manning, Prabhakar Raghavan, and Hinrich Schütze. Introduction to in- formation retrieval. Natural Language Engineering, 16(1):100-103, 2010.","title":"Introduction to information retrieval","authors":"Christopher Manning, Prabhakar Raghavan, Hinrich Schütze","year":"2010","venue":"Natural Language Engineering","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Mikolov et al., 2013] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. Distributed rep- resentations of words and phrases and their composition- ality. In NIPS, pages 3111-3119, 2013.","title":"Distributed representations of words and phrases and their compositionality","authors":"Mikolov","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mukherjee et al., 2012] Arjun Mukherjee, Bing Liu, and Natalie Glance. Spotting fake reviewer groups in con- sumer reviews. In WWW, pages 191--200, New York, April 2012.","title":"Spotting fake reviewer groups in consumer reviews","authors":"Arjun Mukherjee, Bing Liu, Natalie Glance","year":"2012","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mukherjee et al., 2013a] Arjun Mukherjee, Abhinav Ku- mar, Junhui Liu, Bing Wang, Meichun Hsu, Malu Castel- lanos, and Riddhiman Ghosh. Spotting opinion spammers using behavioral footprints. In SIGKDD, Chicago,USA, August 2013.","title":"Spotting opinion spammers using behavioral footprints","authors":"Mukherjee","year":"2013","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mukherjee et al., 2013b] Arjun Mukherjee, Vivek Venkataraman, Bing Liu, and Natalie Glance. What yelp fake review filter might be doing? In ICWSM, pages 1-12, 2013.","title":"What yelp fake review filter might be doing?","authors":"Mukherjee","year":"2013","venue":"ICWSM","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ott et al., 2011] Myle Ott, Yejin Choi, Claire Cardie, and Jeffrey T Hancock. Finding deceptive opinion spam by any stretch of the imagination. In ACL-HLT, pages 309- 319, 2011.","title":"Finding deceptive opinion spam by any stretch of the imagination","authors":"Myle Ott, Yejin Choi, Claire Cardie, Jeffrey T Hancock","year":"2011","venue":"ACL-HLT","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Perozzi et al., 2014] Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: Online learning of social rep- resentations. In SIGKDD, pages 701-710, 2014.","title":"Deepwalk: Online learning of social representations","authors":"Bryan Perozzi, Rami Al-Rfou, Steven Skiena","year":"2014","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rayana and Akoglu, 2015] Shebuti Rayana and Leman Akoglu. Collective opinion spam detection: Bridging re- view networks and metadata. In SIGKDD, pages 985-- 994, Sydney, NSW, Australia, August 2015.","title":"Shebuti Rayana and Leman Akoglu. Collective opinion spam detection: Bridging review networks and metadata","authors":"Akoglu Rayana","year":"2015","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shojaee et al., 2015] Somayeh Shojaee, Azreen Azman, Masrah Murad, Nurfadhlina Sharef, and Nasir Sulaiman. A framework for fake review annotation. In UKSIM- AMSS, pages 153-158, 2015.","title":"A framework for fake review annotation","authors":"Somayeh Shojaee, Azreen Azman, Masrah Murad, Nurfadhlina Sharef, Nasir Sulaiman","year":"2015","venue":"UKSIM-AMSS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tang et al., 2015] Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. Line: Large- scale information network embedding. In WWW, pages 1067-1077, 2015.","title":"Line: Largescale information network embedding","authors":"Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, Qiaozhu Mei","year":"2015","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2011] Guan Wang, Sihong Xie, Bing Liu, and S Yu Philip. Review graph based online store review spam- mer detection. In ICDM, pages 1242-1247. IEEE, 2011.","title":"Review graph based online store review spammer detection","authors":"Guan Wang, Sihong Xie, Bing Liu, S Yu, Philip","year":"2011","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2012] Guan Wang, Sihong Xie, Bing Liu, and Philip S Yu. Identify online store review spammers via social review graph. ACM TIST, 3(4):61:1-61:21, 2012.","title":"Identify online store review spammers via social review graph","authors":"Guan Wang, Sihong Xie, Bing Liu, Philip S Yu","year":"2012","venue":"ACM TIST","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2016] Zhuo Wang, Tingting Hou, Dawei Song, Zhun Li, and Tianqi Kong. Detecting review spammer groups via bipartite graph projection. The Computer Jour- nal, 59(6):861-874, 2016.","title":"Detecting review spammer groups via bipartite graph projection","authors":"Zhuo Wang, Tingting Hou, Dawei Song, Zhun Li, Tianqi Kong","year":"2016","venue":"The Computer Journal","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2018a] Zhuo Wang, Songmin Gu, and Xiaowei Xu. Gslda: Lda-based group spamming detection in prod- uct reviews. Applied Intelligence, 48(9):3094-3107, 2018.","title":"Gslda: Lda-based group spamming detection in product reviews","authors":"Wang","year":"2018","venue":"Applied Intelligence","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2018b] Zhuo Wang, Songmin Gu, Xiangnan Zhao, and Xiaowei Xu. Graph-based review spammer group detection. KIAS, 55(3):571-597, Jun 2018.","title":"Graph-based review spammer group detection","authors":"Wang","year":"2018","venue":"KIAS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xu and Zhang, 2015] Chang Xu and Jie Zhang. Towards collusive fraud detection in online reviews. In ICDM, pages 1051-1056, 2015.","title":"Towards collusive fraud detection in online reviews","authors":"Chang Xu, Jie Zhang","year":"2015","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xu et al., 2013] Chang Xu, Jie Zhang, Kuiyu Chang, and Chong Long. Uncovering collusive spammers in chinese review websites. In CIKM, pages 979-988, 2013.","title":"Uncovering collusive spammers in chinese review websites","authors":"Chang Xu, Jie Zhang, Kuiyu Chang, Chong Long","year":"2013","venue":"CIKM","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}