Lean persuasive design of electronic word-of-mouth (e-WOM) indexes for e-commerce stores based on fogg behavior model

Modeling the persuasiveness of electronic word-of-mouth (e-WOM) indexes helps e-sellers to implement lean persuasive design and shape consumers’ behaviors. This paper develops a quantitative and flexible Fogg Behavior Model for Consumer Purchase Decision-making (FBMCPD) to finely depict the non-linear and the threshold effect of the persuasiveness of e-WOM indexes during the three-stage consumers’ decision-making process. The FBMCPD captures the characteristics of decision-making in each stage including the Halo effect and loss aversion, by introducing various non-linear functions. A hybrid genetic algorithm–particle swarm optimization (GA-PSO) algorithm is proposed to find the model that fits best. Based on the FBMCPD, the four hierarchies of index importance are constructed and the lean improvement curves are plotted, providing guidelines for lean e-WOM indexes persuasive design for online stores. Using data from Taobao.com, the experiment results show that FBMCPD performs better in describing consumers’ purchase behavior and improving e-WOM indexes’ persuasive design.