Opinion Fraud Detection in Online Reviews by Network Effects
Proceedings of the International AAAI Conference on Web and Social MediaPublished 3 August 2021Open access
Leman Akoglu, Rishi Chandy, Christos Faloutsos
Citations400
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A fast and effective framework for spotting fraudsters and fake reviews in online review datasets, FRAUDEAGLE, which exploits the network effect among reviewers and products and is scalable to large datasets as its run time grows linearly with network size.
Abstract
User-generated online reviews can play a significant role in the success of retail products, hotels, restaurants, etc. However,review systems are often targeted by opinion spammers who seek to distort the perceived quality of a product by creating fraudulent reviews. We propose a fast and effective framework, FRAUDEAGLE, for spotting fraudsters and fake reviews in online review datasets. Our method has several advantages: (1) it exploits the network effect among reviewers and products, unlike the vast majority of existing methods that focus on review text or behavioral analysis, (2) it consists of two complementary steps; scoring users and reviews for fraud detection, and grouping for visualization and sensemaking, (3) it operates in a completely unsupervised fashion requiring no labeled data, while still incorporating side information if available, and (4) it is scalable to large datasets as its run time grows linearly with network size. We demonstrate the effectiveness of our framework on syntheticand real datasets; where FRAUDEAGLE successfully reveals fraud-bots in a large online app review database.
Keywords
Computer Science
Journal of the ACMAuthoritative sources in a hyperlinked environment
9,060 Citations1999Jon Kleinberg
This work proposes and test an algorithmic formulation of the notion of authority, based on the relationship between a set of relevant authoritative pages and the set of “hub pages” that join them together in the link structure, and has connections to the eigenvectors of certain matrices associated with the link graph.
Thumbs up?
6,987 Citations2002Bo Pang, Lillian Lee +1 more
This work considers the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, and concludes by examining factors that make the sentiment classification problem more challenging.
arXiv (Cornell University)Thumbs up? Sentiment Classification using Machine Learning Techniques
2,208 Citations2002Bo Pang, Lillian Lee +1 more
Symposium on Discrete AlgorithmsAuthoritative sources in a hyperlinked environment
1,836 Citations1998Jon Kleinberg
Opinion spam and analysis
1,520 Citations2008Nitin Jindal, Bing Liu
It is shown that opinion spam is quite different from Web spam and email spam, and thus requires different detection techniques, and therefore requires some novel techniques to detect them.
Collaborative filtering with temporal dynamics
1,170 Citations2009Yehuda Koren
Two leading collaborative filtering recommendation approaches are revamp and a more sensitive approach is required, which can make better distinctions between transient effects and long term patterns.
Twitter under crisis
943 Citations2010Marcelo Mendoza, Bárbara Poblete +1 more
The behavior of Twitter users under an emergency situation is explored and it is shown that it is posible to detect rumors by using aggregate analysis on tweets, and that the propagation of tweets that correspond to rumors differs from tweets that spread news.
Spotting fake reviewer groups in consumer reviews
747 Citations2012Arjun Mukherjee, Bing Liu +1 more
This paper studies spam detection in the collaborative setting, i.e., to discover fake reviewer groups by using several behavioral models derived from the collusion phenomenon among fake reviewers and relation models based on the relationships among groups, individual reviewers, and products they reviewed to detectfake reviewer groups.
Detecting product review spammers using rating behaviors
720 Citations2010Ee‐Peng Lim, Viet-An Nguyen +3 more
This paper identifies several characteristic behaviors of review spammers and model these behaviors so as to detect the spammers, and shows that the detected spammers have more significant impact on ratings compared with the unhelpful reviewers.
arXiv (Cornell University)Finding Deceptive Opinion Spam by Any Stretch of the Imagination
688 Citations2011Myle Ott, Yejin Choi +2 more
Lecture notes in computer scienceLink Prediction via Matrix Factorization
533 Citations2011Aditya Krishna Menon, Charles Elkan
The model learns latent features from the topological structure of a (possibly directed) graph, and is shown to make better predictions than popular unsupervised scores, and may be combined with optional explicit features for nodes or edges, which yields better performance.
Syntactic Stylometry for Deception Detection
414 Citations2012Song Feng, Ritwik Banerjee +1 more
This paper investigates syntactic stylometry for deception detection, adding a somewhat unconventional angle to prior literature and demonstrating that features driven from Context Free Grammar (CFG) parse trees consistently improve the detection performance over several baselines that are based only on shallow lexico-syntactic features.
Review spam detection via temporal pattern discovery
400 Citations2012Sihong Xie, Guan Wang +2 more
It is discovered that singleton review is a significant source of spam reviews and largely affects the ratings of online stores and a hierarchical algorithm is proposed to robustly detect the time windows where such attacks are likely to have happened.
Netprobe
383 Citations2007Shashank Pandit, Duen Horng Chau +2 more
This paper describes the design and implementation of NetProbe, a system that is a Markov Random Field tuned to detect the suspicious patterns that fraudsters create, and employs a Belief Propagation mechanism to detect likely fraudsters.
Review Graph Based Online Store Review Spammer Detection
382 Citations2011Guan Wang, Sihong Xie +2 more
This paper proposes a novel concept of a heterogeneous review graph to capture the relationships among reviewers, reviews and stores that the reviewers have reviewed, and explores how interactions between nodes in this graph can reveal the cause of spam.
Finding unusual review patterns using unexpected rules
339 Citations2010Nitin Jindal, Bing Liu +1 more
Using the technique, an Amazon.com review dataset is analyzed and many unexpected rules and rule groups which indicate spam activities are found.
Learning to identify review spam
332 Citations2011Fangtao Li, Minlie Huang +2 more
This paper exploits machine learning methods to identify review spam and provides a twoview semi-supervised method, co-training, to exploit the large amount of unlabeled data and shows that the proposed method is effective.
A Simple Relational Classifier
246 Citations2003Sofus A. Macskassy, Foster Provost
It is argued that a simple relational predictive model the predicts only based on class labels of related neighbors, using no learning and no inherent attributes should be used as a baseline to assess the performance of relational learners.
Fully automatic cross-associations
244 Citations2004Deepayan Chakrabarti, Spiros Papadimitriou +2 more
This work furnishes a clear, information-theoretic criterion to choose a good cross-association as well as its parameters, namely, the number of row and column groups, and provides scalable algorithms to approach the optimal.
Proceedings of the International AAAI Conference on Web and Social MediaDistributional Footprints of Deceptive Product Reviews
217 Citations2021Song Feng, Longfei Xing +2 more
A range of experiments confirm the hypothesized connection between the distributional anomaly and deceptive reviews and provide novel quantitative insights into the characteristics of natural distributions of opinions in the TripAdvisor hotel review and the Amazon product review domains.
Using relational knowledge discovery to prevent securities fraud
113 Citations2005Jennifer Neville, Özgür Şimşek +4 more
Using statistical relational learning algorithms, models that rank brokers with respect to the probability that they would commit a serious violation of securities regulations in the near future are developed and found to correlate highly with the subjective evaluations of experienced NASD examiners.
SNARE
86 Citations2009Mary McGlohon, Stephen D. Bay +3 more
This work builds upon the belief propagation algorithm for use in detecting collusion and other fraud schemes, and proposes an algorithm called SNARE (Social Network Analysis for Risk Evaluation), which is robust to the choice of parameters and highly scalable-linearly with the number of edges in a graph.
Data Mining and Knowledge DiscoveryRTG: a recursive realistic graph generator using random typing
68 Citations2009Leman Akoglu, Christos Faloutsos
A new, recursive model to generate realistic graphs, evolving over time, that mimics two real-world graphs very well and shows how to handle time so that edge/weight additions are bursty and self-similar.
Lecture notes in computer scienceRTG: A Recursive Realistic Graph Generator Using Random Typing
48 Citations2009Leman Akoglu, Christos Faloutsos
KiltHub RepositoryNetProbe: A Fast and Scalable System for Fraud Detection in Online Auction Networks
32 Citations2018Shashank Pandit, Duen Horng Chau +2 more
Mining and Learning with GraphsLearning and Inference in Massive Social Networks
16 Citations2007Shawndra Hill, Foster Provost +1 more
In this context each treatment is unmatched, and the analyst’s challenge is to maintain a conscientious stance within waves of intermittent “push-pull” between subject/object and elemental structures.