Detecting fake reviewers in heterogeneous networks of buyers and sellers: a collaborative training-based spammer group algorithm

Cybersecurity

Table 1 A summary of existing work on spammer group detection

Method	Classification dimension
	The strategy used to generate candidate groups			Considered features			The coupling degrees of group members		The concentrations of the attacked target products
	FIM-based	Graph-based		B&C	S	B&C+S	Tightly-coupled	Loosely-coupled	Single-product	Cross-product
	FIM-based	Homogeneous	Heterogeneous	B&C	S	B&C+S	Tightly-coupled	Loosely-coupled	Single-product	Cross-product
Mukherjee et al. (2012)	√
Shehnepoor et al. (2022)	√				√		√
Ji et al. (2020)				√					√
Xu et al. (2013)	√			√			√
Zhang et al. (2021)	√					√	√
Shehnepoor et al. (2021)	√					√	√
Wang et al. (2016)		√				√		√
Wang et al. (2018)		√				√		√
Li et al. (2017)		√		√				√
Zhang et al. (2022a)		√				√		√
Hu (2021)				√				√
Zhang et al. (2020a)		√		√				√
Akoglu et al. (2013)			√			√		√
Ye et al. (2015)			√		√			√
Zheng et al. (2018)			√		√			√
Zhu et al. (2019)					√			√
Chao et al. (2022)			√			√		√
Zhang et al. (2022b)			√		√			√
SGDCTH (Ours)			√			√		√		√