User-based Network Embedding for Collective Opinion Spammer Detection

Due to the huge commercial interests behind online reviews, a tremendousamount of spammers manufacture spam reviews for product reputation manipulation. To further enhance the influence of spam reviews, spammers often collaboratively post spam reviewers within a short period of time, the activities of whom are called collective opinion spam campaign. As the goals and members of the spam campaign activities change frequently, and some spammers also imitate normal purchases to conceal identity, which makes the spammer detection challenging. In this paper, we propose an unsupervised network embedding-based approach to jointly exploiting different types of relations, e.g., direct common behaviour relation and indirect co-reviewed relation to effectively represent the relevances of users for detecting the collective opinion spammers. The average improvements of our method over the state-of-the-art solutions on dataset AmazonCn and YelpHotel are [14.09%,12.04%] and [16.25%,12.78%] in terms of AP and AUC, respectively.

[1]  H. Sebastian Seung,et al.  Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks , 2003, Neural Computation.

[2]  Minhwan Yu,et al.  Deep Semantic Frame-Based Deceptive Opinion Spam Analysis , 2015, CIKM.

[3]  Claire Cardie,et al.  Finding Deceptive Opinion Spam by Any Stretch of the Imagination , 2011, ACL.

[4]  Massimo Poesio,et al.  Identifying fake Amazon reviews as learning from crowds , 2014, EACL.

[5]  Yejin Choi,et al.  Syntactic Stylometry for Deception Detection , 2012, ACL.

[6]  Ee-Peng Lim,et al.  Detecting product review spammers using rating behaviors , 2010, CIKM.

[7]  Philip S. Yu,et al.  Review spam detection via temporal pattern discovery , 2012, KDD.

[8]  Richard Hans Robert Hahnloser,et al.  Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[9]  Arjun Mukherjee,et al.  On the Temporal Dynamics of Opinion Spamming: Case Studies on Yelp , 2016, WWW.

[10]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[11]  Chuan Zhou,et al.  FraudNE: a Joint Embedding Approach for Fraud Detection , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[12]  Christos Faloutsos,et al.  Robust multivariate autoregression for anomaly detection in dynamic product ratings , 2014, WWW.

[13]  Leman Akoglu,et al.  Collective Opinion Spam Detection using Active Inference , 2016, SDM.

[14]  Arjun Mukherjee,et al.  Spotting Fake Reviews using Positive-Unlabeled Learning , 2014, Computación y Sistemas.

[15]  Christos Faloutsos,et al.  HoloScope: Topology-and-Spike Aware Fraud Detection , 2017, CIKM.

[16]  Claire Cardie,et al.  Towards a General Rule for Identifying Deceptive Opinion Spam , 2014, ACL.

[17]  Anna Cinzia Squicciarini,et al.  Combating Crowdsourced Review Manipulators: A Neighborhood-Based Approach , 2018, WSDM.

[18]  Leman Akoglu,et al.  Discovering Opinion Spammer Groups by Network Footprints , 2015, ECML/PKDD.

[19]  Jie Zhang,et al.  Online Reputation Fraud Campaign Detection in User Ratings , 2017, IJCAI.

[20]  Leman Akoglu,et al.  Collective Opinion Spam Detection: Bridging Review Networks and Metadata , 2015, KDD.

[21]  Jun Zhao,et al.  Learning to Represent Review with Tensor Decomposition for Spam Detection , 2016, EMNLP.

[22]  Xiaolong Wang,et al.  Opinion spam detection by incorporating multimodal embedded representation into a probabilistic review graph , 2019, Neurocomputing.

[23]  Jie Zhang,et al.  Combating Product Review Spam Campaigns via Multiple Heterogeneous Pairwise Features , 2015, SDM.

[24]  Chong Long,et al.  Uncovering collusive spammers in Chinese review websites , 2013, CIKM.

[25]  Jure Leskovec,et al.  Predicting positive and negative links in online social networks , 2010, WWW '10.

[26]  Yi Yang,et al.  Learning to Identify Review Spam , 2011, IJCAI.

[27]  Christos Faloutsos,et al.  Detecting anomalies in dynamic rating data: a robust probabilistic model for rating evolution , 2014, KDD.

[28]  Christos Faloutsos,et al.  REV2: Fraudulent User Prediction in Rating Platforms , 2018, WSDM.

[29]  Zhuo Wang,et al.  ColluEagle: collusive review spammer detection using Markov random fields , 2020, Data Mining and Knowledge Discovery.

[30]  Qiang Wu,et al.  Unsupervised User Behavior Representation for Fraud Review Detection with Cold-Start Problem , 2019, PAKDD.

[31]  Yue Zhang,et al.  Deceptive Opinion Spam Detection Using Neural Network , 2016, COLING.

[32]  Arjun Mukherjee,et al.  What Yelp Fake Review Filter Might Be Doing? , 2013, ICWSM.

[33]  Arjun Mukherjee,et al.  Analyzing and Detecting Opinion Spam on a Large-scale Dataset via Temporal and Spatial Patterns , 2015, ICWSM.

[34]  Ee-Peng Lim,et al.  Finding unusual review patterns using unexpected rules , 2010, CIKM.

[35]  Bing Liu,et al.  An Attribute Enhanced Domain Adaptive Model for Cold-Start Spam Review Detection , 2018, COLING.

[36]  Santhosh Kumar,et al.  Temporal Opinion Spam Detection by Multivariate Indicative Signals , 2016, ICWSM.

[37]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[38]  Christopher G. Harris.  Detecting Deceptive Opinion Spam Using Human Computation , 2012, HCOMP@AAAI.

[39]  Reza Farahbakhsh,et al.  NetSpam: A Network-Based Spam Detection Framework for Reviews in Online Social Media , 2017, IEEE Transactions on Information Forensics and Security.

[40]  Arjun Mukherjee,et al.  Spotting fake reviewer groups in consumer reviews , 2012, WWW.

[41]  Weixiang Shao,et al.  Bimodal Distribution and Co-Bursting in Review Spam Detection , 2017, WWW.