Discovering Opinion Spammer Groups by Network Footprints

Ye, Junting; Akoglu, Leman

doi:10.1007/978-3-319-23528-8_17

Cited by 95 publications

(78 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, with respect to prior work, it does not improve the spam/spammer detection accuracy. In a recent work, Ye and Akoglu propose GroupStrainer , a two‐step method to discover group spammers and their targeted products. The considered review network is a bipartite graph consisting of reviewer nodes connected to product nodes through review relations.…”

Section: Approaches To Credibility Assessmentmentioning

confidence: 99%

Credibility in social media: opinions, news, and health information—a survey

Viviani

Pasi

2017

WIREs Data Min & Knowl

154

View full text Add to dashboard Cite

In the Social Web scenario, where large amounts of User Generated Content diffuse through Social Media, the risk of running into misinformation is not negligible. For this reason, assessing and mining the credibility of both sources of information and information itself constitute nowadays a fundamental issue. Credibility, also referred as believability, is a quality perceived by individuals, who are not always able to discern with their cognitive capacities genuine information from the fake one. For this reason, in the recent years several approaches have been proposed to automatically assess credibility in Social Media. Most of them are based on data‐driven models, i.e., they employ machine‐learning techniques to identify misinformation, but recently also model‐driven approaches are emerging, as well as graph‐based approaches focusing on credibility propagation. Since multiple social applications have been developed for different aims and in different contexts, several solutions have been considered to address the issue of credibility assessment in Social Media. Three of the main tasks facing this issue and considered in this article concern: (1) the detection of opinion spam in review sites, (2) the detection of fake news and spam in microblogging, and (3) the credibility assessment of online health information. Despite the high number of interesting solutions proposed in the literature to tackle the above three tasks, some issues remain unsolved; they mainly concern both the absence of predefined benchmarks and gold standard datasets, and the difficulty of collecting and mining large amount of data, which has not yet received the attention it deserves. WIREs Data Mining Knowl Discov 2017, 7:e1209. doi: 10.1002/widm.1209 This article is categorized under: Algorithmic Development > Web Mining Application Areas > Science and Technology Technologies > Machine Learning

show abstract

Section: Approaches To Credibility Assessmentmentioning

confidence: 99%

Credibility in social media: opinions, news, and health information—a survey

Viviani

Pasi

2017

WIREs Data Min & Knowl

154

View full text Add to dashboard Cite

show abstract

“…Wang et al [24] first introduce review graph to capture the relationships between entities. Spotting fraudster groups were then explored by network footprints [27], community discovery with sentiment analysis [2], social interactions for sparse group [26]. In-depth, Hooi et al [6] proposes an advanced dense subgraph mining for group fraudsters detection, targeting on detecting camouflage or hijacked accounts who manipulate their writing to look just like normal users.…”

Section: Related Work 21 Fraud Review Detectionmentioning

confidence: 99%

“…Recent years have seen significant progress made in fraud detection. Current efforts mainly focused on extracting linguistic features (n-grams, POS, etc) and behavioral features [27,5]. However, linguistic features are ineffective when dealing with real-life fraud reviews [19], especially when linguistic features are easy to be imitated, a.k.a.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised User Behavior Representation for Fraud Review Detection with Cold-Start Problem

Zhu

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Detecting fraud review is becoming extremely important in order to provide reliable information in cyberspace, in which, however, handling cold-start problem is a critical and urgent challenge since the case of cold-start fraud review rarely provides sufficient information for further assessing its authenticity. Existing work on detecting cold-start cases relies on the limited contents of the review posted by the user and a traditional classifier to make the decision. However, simply modeling review is not reliable since reviews can be easily manipulated. Also, it is hard to obtain high-quality labeled data for training the classifier. In this paper, we tackle cold-start problems by (1) using a user's behavior representation rather than review contents to measure authenticity, which further (2) consider user social relations with other existing users when posting reviews. The method is completely (3) unsupervised. Comprehensive experiments on Yelp data sets demonstrate our method significantly outperforms the state-of-the-art methods.

show abstract

“…FairPlay's use app authorizations varies from existing work its specialise in the temporal dimension, e.g., modifications within the selection of requested approvals, most importantly the "hazardous" ones. we have a tendency to observe that FairPlay identifies as well as makes use of a replacement relationship between malware and search ranking fraud.2.2 Graph mainly Viewpoint Spam Discovery Chart based approaches are prepared to tackle point of view spam [13], [14] Ye and Akoglu [24] evaluate the possibility of a product to be a spam project target, after that cluster spammers on a 2-hop subgraph evoked by the item with the very best chance worths. Akoglu et al [14] frame fraud detection as an authorized network classification downside as well as classify users and also product, that kind a bipartite network, employing a propagation-based mathematical program FairPlay's family member strategy varies because it identifies apps assessed during a contiguous amount, by teams of users with a history of evaluating apps alike.…”

Section: Related Workmentioning

confidence: 99%

Finding Grade Fake and Virus Identifying in Play Store

2019

IJITEE

View full text Add to dashboard Cite

Deceitful behaviors in Google Play, the leading favored robot application market, fuel search ranking misuse as well as malware proliferation. to spot malware, previous job has actually centred on application practicable and also permission analysis. during this paper, we often tend to introduce Justice, a distinct system that finds and leverages traces left by scammers, to sight each malware as well as applications based on go looking rank fraudulence. Fair game correlates review tasks as well as unambiguously incorporates identified testimonial relations with linguistic and also task signals obtained from Google Play application expertise (87 K applications, 2.9 M evaluations, and 2.4 M customers, gathered over 0.5 a year), to spot suspicious applications. Fair game attains over ninety-five plc. accuracy in categorizing gold normal datasets of malware, unethical as well as Bonafede apps. we tend to reveal that seventy-five plc. of the identified malware apps have interaction in search rank fraud. Fair Play discovers numerous dishonest applications that presently escape Google Baby bouncer's detection innovation. Fair Play furthermore helped the creation of rather one,000 reviews, reportable for 193 apps, that reveal a new sort of "forceful" review project: users are troubled into composing favorable evaluations and also mount as well as assess alternative applications.

show abstract

Discovering Opinion Spammer Groups by Network Footprints

Cited by 95 publications

References 20 publications

Credibility in social media: opinions, news, and health information—a survey

Credibility in social media: opinions, news, and health information—a survey

Unsupervised User Behavior Representation for Fraud Review Detection with Cold-Start Problem

Finding Grade Fake and Virus Identifying in Play Store

Contact Info

Product

Resources

About