Sequential mediation of parasocial relationships for purchase intention: PLS-SEM and machine learning approach

TL;DR

This study explores how social media influencers' credibility influences purchase intentions through parasocial relationships, using PLS-SEM and machine learning across European and Southeast Asian samples.

Contribution

It introduces a combined PLS-SEM and machine learning approach to analyze factors affecting purchase intentions via parasocial relationships in social media marketing.

Findings

Trustworthiness and expertise are key factors in source influence.

Benign envy significantly predicts purchase intention.

Audience-related features outperform brand-related features in prediction.

Abstract

Companies employ social media influencers SMIs due to the compelling evidence of their advertising effectiveness, however, more research is required to identify and compare factors driving their success.We investigate the effect of source influence SI on the intention to purchase I2P through the sequential mediation of parasocial relationships PSR with benign envy BE and PSR with the perceived brand influencer fit BIF.Two independent samples N=411; N=355 from Europe and Southeast Asia are used to perform: i PLSSEM analysis to obtain the model's predictive power and ii classification based machine learning ML to evaluate the model's accuracy. Moreover, within study and between studies comparative analyses are performed. We use regression analysis and split test ML technique for validation. Both samples indicate a higher role of trustworthiness and expertise in forming SI. Furthermore, comparative mediation analysis and predictive accuracy scores show that the audience related feature, BE, played a more vital role in affecting/predicting the followers' I2P than the brand-related feature, BIF. Our findings contribute to the knowledge of SMIs' credibility and comparative analysis paradigms and provide a better understanding for marketing practitioners and researchers.