Opinion Fraud Detection in Online Reviews by Network Effects

By Leman Akoglu, Rishi Chandy, Christos Faloutsos. 2013

456 citations recorded by the source corpus.

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.

Subfields: Computer Networks and Communications, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Signal Processing

Citations in the corpus

Attacking Graph-based Classification via Manipulating the Graph Structure (2019, methodology): “putation scores. In particular, state-of-the-art collective classification methods include Random Walk (RW) based methods [9, 10, 30, 36, 40, 72, 74, 76], Loopy Belief Propagation (LBP) based methods [1, 14, 23, 25, 47, 59], LinearizedLoopyBeliefPropagation(LinLBP)based methods [37, 64], and Joint W”
Graph based anomaly detection and description: a survey (2014, background): “…and Liu, 2008, Jindal et al., 2010, Xie et al., 2012], (ii) language stylometry analysis to spot deception [Feng et al., 2012a, Ott et al., 2011], and (iii) relational analysis and network effects to exploit connections among fraudulent reviewers [Akoglu et al., 2013a, Wang et al., 2011a, 2012a].”
Fake News: A Survey of Research, Detection Methods, and Opportunities (2018, background): “, reviewers write reviews in the same burst); the network in [Akoglu et al. 2013] is bipartite, where reviewers and products are connected in terms of positive (+) or negative (−) reviews a reviewer has posted for a product (see Figure 9(a) for the illustration).”
Identity-aware Graph Neural Networks (2021, background): “A broad range of application domains, such as network fraud detection (Akoglu, Chandy, and Faloutsos 2013; Kumar, Cheng, and Leskovec 2017; Akoglu and Faloutsos 2013), molecular drug structure discovery (You et al. 2018a,b; Jin, Barzilay, and Jaakkola 2018), recommender systems (Ying et al. 2018;…”
Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation (2018, methodology): “Speciﬁcally, most existing methods [2], [3], [5], [13], [15], [17]–[20], [23]–[25], [29] simply set a large constant weight to all edges, ignoring the difference between homogeneous and heterogeneous edges.”
On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection (2018, background): “ create the first sizable dataset in deception detection by asking Amazon Mechanical Turkers to write deceptive reviews. Deceptive reviews can also be seen as an instance of spamming and online fraud [2, 16, 27, 56]. More recently, the issue of misinformation and fake news has drawn much attention f”
Collective Opinion Spam Detection: Bridging Review Networks and Metadata (2015, methodology): “[1] proposed a detection framework based on Markov Random Field (MRF) models on the signed bi-partite network of users and products, which are connected through positive or negative review relations (signed edges).”
FRAUDAR: Bounding Graph Fraud in the Face of Camouflage (2016, methodology): “BP has been used for fraud classiﬁ-cation on eBay [21], and fraud detection [1].”
Fake It Till You Make It: Reputation, Competition, and Yelp Review Fraud (2016, unknown): “…developing data-mining algorithms that leverage observable review characteristics, such as textual features, and reviewers’ social networks, to identify abnormal reviewing patterns (for example, see Feng et al. (2012), Akoglu et al. (2013), Mukherjee et al. (2011, 2012), and Jindal et al. (2010)).”
REV2: Fraudulent User Prediction in Rating Platforms (2018, background): “• SpEagle [26] incorporates behavior features (user, rating text, and product) into FraudEagle, and the final spam scores of users are used for ranking.”
False Information on Web and Social Media: A Survey (2018, unknown): “Figure reprinted with permission from [5].”
APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions (2015, background): “Our approach discusses the sanity check, and can be implemented both in an on-line as an offline environment.”
Anomaly detection in online social networks (2014, methodology): “…Bichler (2011); Cheng and Dickinson (2013)), clandestine organisational structures (e.g. Shetty and Adibi (2005); Krebs (2002); Reid et al. (2005)), and fraudulent and predatory activity (e.g. Phua et al. (2010); Fire et al. (2012); Chau et al. (2006); Akoglu et al. (2013); Pandit et al. (2007)).”