Spam Review Detection Techniques: A Systematic Literature Review

Hussain, Naveed; Mirza, Hamid Turab; Rasool, Ghulam; Hussain, Ibrar; Kaleem, Mohammad

doi:10.3390/app9050987

Cited by 72 publications

(34 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Systematic literature review (SLR) provides answers to certain research questions [11]. The stages in a systematic literature review are shown in Figure 1.…”

Section: Methodsmentioning

confidence: 99%

Experiments in Physics Learning in the COVID-19 Era: Systematic Literature Review

Aththibby¹,

Kuswanto²,

Mundilarto³

2021

Advances in Social Science, Education and Humanities Research

View full text Add to dashboard Cite

The COVID-19 pandemic has influenced global conditions globally, including in the world of education in Indonesia. The implication of the COVID-19 pandemic is learning that initially focused on face-to-face shifting to distance learning / online learning. This condition is also a challenge in learning physics. This is inseparable from learning physics which requires experimental activities therein. This article will review the potential use of various platforms in solving laboratory-based physics learning problems in the COVID-19 pandemic era. To produce a comprehensive analysis of this potential picture, a systematic literature review is conducted. The analysis shows that various platforms are very potential in solving physics learning problems that require experiments for physics teachers in the pandemic era COVID-2019.

show abstract

“…Systematic literature review (SLR) provides answers to certain research questions [11]. The stages in a systematic literature review are shown in Figure 1.…”

Section: Methodsmentioning

confidence: 99%

Experiments in Physics Learning in the COVID-19 Era: Systematic Literature Review

Aththibby¹,

Kuswanto²,

Mundilarto³

2021

Advances in Social Science, Education and Humanities Research

View full text Add to dashboard Cite

show abstract

“…This section elaborates the proposed spammer behavioral method and analyzes the performance of the method in terms of accurate identification of spam reviews. Since a spammer can be identified by analyzing its different behavioral features, therefore, unlabelled dataset can be used with unsupervised learning to identify the spam reviews [31], [32]. The proposed Spammer Behavioral Method (SRD-BM) takes unlabelled dataset and produces an output of a labelled dataset that identifies spam and not spam reviews.…”

Section: Spam Review Detection Using the Spammer Behavioral Methomentioning

confidence: 99%

Spam Review Detection Using the Linguistic and Spammer Behavioral Methods

et al. 2020

Self Cite

View full text Add to dashboard Cite

Online reviews regarding different products or services have become the main source to determine public opinions. Consequently, manufacturers and sellers are extremely concerned with customer reviews as these have a direct impact on their businesses. Unfortunately, to gain profits or fame, spam reviews are written to promote or demote targeted products or services. This practice is known as review spamming. In recent years, the spam review detection problem has gained much attention from communities and researchers, but still there is a need to perform experiments on real-world large-scale review datasets. This can help to analyze the impact of widespread opinion spam in online reviews. In this work, two different spam review detection methods have been proposed: (1) Spam Review Detection using Behavioral Method (SRD-BM) utilizes thirteen different spammer's behavioral features to calculate the review spam score which is then used to identify spammers and spam reviews, and (2) Spam Review Detection using Linguistic Method (SRD-LM) works on the content of the reviews and utilizes transformation, feature selection and classification to identify the spam reviews. Experimental evaluations are conducted on a real-world Amazon review dataset which analyze 26.7 million reviews and 15.4 million reviewers. The evaluations show that both proposed models have significantly improved the detection process of spam reviews. Specifically, SRD-BM achieved 93.1% accuracy whereas SRD-LM achieved 88.5% accuracy in spam review detection. Comparatively, SRD-BM achieved better accuracy because it works on utilizing rich set of spammers behavioral features of review dataset which provides in-depth analysis of spammer behaviour. Moreover, both proposed models outperformed existing approaches when compared in terms of accurate identification of spam reviews. To the best of our knowledge, this is the first study of its kind which uses large-scale review dataset to analyze different spammers' behavioral features and linguistic method utilizing different available classifiers. INDEX TERMS Online product reviews, spam reviews, spam review detection, linguistic features, spammer behavioral features.

show abstract

“…Each node is divided into sub-categories by defining the level of categorization. Hussain et al [10] detail the spam review detection techniques in 2-4 level tree depth. Meanwhile, Gupta et al [11] present multiple taxonomies related to phishing attacks.…”

Section: Visualization Forms Of Phishing Attack Taxonomiesmentioning

confidence: 99%

E-mail-Based Phishing Attack Taxonomy

et al. 2020

View full text Add to dashboard Cite

The amount of fraud on the Internet is increasing along with the availability and the popularity of the Internet around the world. One of the most common forms of Internet fraud is phishing. Phishing attacks seek to obtain a user’s personal or secret information. The variety of phishing attacks is very broad, and usage of novel, more sophisticated methods complicates its automated filtering. Therefore, it is important to form up-to-date and detailed phishing attack taxonomy, which could be used for both human education purposes as well as phishing attack discrete notation. In this paper, we propose an e-mail-based phishing attack taxonomy, which includes six phases of the attack. Each phase has at least one criterion for the attack categorization. Each category is described, and in some cases the categories have sub-classes to present the full variety of phishing attacks. The proposed taxonomy is compared to similar taxonomies. Our taxonomy outperforms other phishing attack taxonomies in numbers of phases, criteria and distinguished classes. Validation of the proposed taxonomy is achieved by adapting it as a phishing attack notation for an incident management system. Taxonomy usage for phishing attack notation increases the level of description of phishing attacks compared to free-form phishing attack descriptions.

show abstract

Spam Review Detection Techniques: A Systematic Literature Review

Cited by 72 publications

References 67 publications

Experiments in Physics Learning in the COVID-19 Era: Systematic Literature Review

Experiments in Physics Learning in the COVID-19 Era: Systematic Literature Review

Spam Review Detection Using the Linguistic and Spammer Behavioral Methods

E-mail-Based Phishing Attack Taxonomy

Contact Info

Product

Resources

About