Detection of review spam: A survey

Heydari, Atefeh; Tavakoli, Mohammad Ali; Salim, Naomie; Heydari, Zahra

doi:10.1016/j.eswa.2014.12.029

Cited by 243 publications

(151 citation statements)

References 11 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…Previous work by [8] , proposes a Bayesian framework, which is theoretical efficient and practically reasonable method of combination, when investigating the integration of text and image classifiers. [9], there are limited studies on spam detection. Problem of effective, efficiency and accuracy in spam detection on social networks and email generally, they try to provide survey and algorithms method to solve the problem pose by the threat.…”

Section: Introductionmentioning

confidence: 99%

“…The main aim of this review is to understand, classify and analyze the existing spam detection on social networks for measuring the quality of spam detection on social networks and its architectural framework, to direct and support future research, while other reviews [9] [2] [7], [74] and [33] aim mainly at provide an overview of quality measure and evaluations. Certainly a difference in goals leads to a different focus.…”

Section: Introductionmentioning

confidence: 99%

“…We based our review on a systematic mapping review, which led to the identification of 36 studies. The review in [9] is based on only 3 articles, and that in [7] is based on only 4 articles. The review in [2] and [74] is based on 9 articles.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Mapping Study to Investigate Spam Detection on Social Networks

Kamoru¹,

Jaafar²,

Murad³

2017

IJAIS

View full text Add to dashboard Cite

Social networks such as Facebook, Twitter and SinaWeibo have become increasingly important for reaching millions of user globally. Consequently, spammers are increasing using such networks for propagating spam. Existing research on filtering techniques such as collaborative filters and behavioral analysis filters are able to significantly reduce spam. In recent years, online social networks have become the most important medium of communication among individual and organization to interact. Unfortunately, driven by the desire to communicate, fraudster or spammers have produced deceptive spam or unsolicited commercial email(UCE). The fraudsters' or spammer activities mislead potential users and victims reshaping their individual life and general communication on social network platform.The aim of this study is to understand, classify and analyze existing research in spam detection on social networks, focusing on approaches and elements that are used to evaluate the general framework of spam detection and its architectural framework from the users perspective, service provider and security analyst 's point of view. This paper presents a systematic mapping study of several spam detection techniques and approaches on social networks that were proposed to measure to evaluate the general framework of spam detection on social networks. We found 17 proposals that could be applied to evaluate spam detection on social networks, while 14 proposals could be applied to evaluate the users, service providers and practitioners. Various elements of spam detection on social networks that were measured are reviewed and discussed. Only a few of the proposed spam detection on social networks are soundly defined. The quality assessment of the primary studies detected many limitations and suggested guidelines for possibilities for improving and increasing the acceptance of spam detection on social networks. However, it remains a challenge to characterize and evaluate a spam detection and framework on social networks quantitatively. For this fact, much effort must be made to achieve a better spam detection approach in the future that will be devoid of problem anomaly detection, fault detection, malware detection and intrusion detection General Terms

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Mapping Study to Investigate Spam Detection on Social Networks

Kamoru¹,

Jaafar²,

Murad³

2017

IJAIS

View full text Add to dashboard Cite

show abstract

“…With the features of pattern recognition, anomaly detection, data analysis, and machine learning, the AIS have recently gained considerable research interest from diverse communities [2]. A weight is assigned to the detector which was decremented or incremented when observing the expression in the spam message.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Email Spam Detection Method Using Negative Selection and Genetic Algorithms

Abdolahnezhad¹,

Banirostam²

2016

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Abstract:In this paper, a new model was proposed to cope with the trend of email spam that improves the generation of a detector in the improved and standard negative selection algorithm (NSA) with the use of stochastic distribution to model the data point using genetic algorithms. The theoretical analysis and the experimental result show that the performance of proposed method is higher than the improved and standard NSA, which the accuracy of the proposed model is 91.90%, while the improved NSA model is 85.27%, and the standard NSA model is 62.75%.

show abstract

“…Fornaciari and Poesio (2012) combine unigrams with LIWC features in Italian court statements to distinguish between truthful and deceptive statements. Heydari et al (2015), Karami and Zhou (2015) and Ott et al (2011) apply a combination of unigrams and the LIWC features to detect spam in reviews. Sun et al (2016) only use bigrams and trigrams to detect review spam.…”

Detection of review spam: A survey

Cited by 243 publications

References 11 publications

A Mapping Study to Investigate Spam Detection on Social Networks

A Mapping Study to Investigate Spam Detection on Social Networks

Hybrid Email Spam Detection Method Using Negative Selection and Genetic Algorithms

Text mining to detect indications of fraud in annual reports worldwide

Contact Info

Product

Resources

About