Modelling the factors influencing e-satisfaction and e-advocacy in organic food services: a hybrid PLS-SEM and ML approach
Dewan Mehrab Ashrafi et al.
What the paper says
Purpose This study aims to respond to the recent calls made for research on customer e-advocacy in online organic food services. It examines how e-satisfaction influences user e-recommendation behaviours and provides insights into increasing customer e-advocacy and market growth in the expanding online organic food services sector. Design/methodology/approach A quantitative research design with a deductive approach was used, and purposive sampling was used to select a relevant sample of 312 online organic food services users. Data were analysed using partial least squares structural equation modelling to assess the relationships between e-satisfaction and e-recommendation behaviours. Additionally, machine learning techniques were used to test the robustness and predictive accuracy and uncover deeper patterns in consumer behaviours. Findings The results show that service recovery mechanisms, logistical efficiency and service guarantees significantly influence e-satisfaction and e-recommendation behaviours in regard to online organic food services. While payment experience was found to affect e-satisfaction, it was not found to directly impact e-recommendation behaviours. Practical implications This study provides actionable insights for online organic food service platforms to increase e-satisfaction and e-recommendation through service recovery mechanisms, logistical efficiency and service guarantees. Managers can implement these findings by prioritising investment in real-time delivery tracking systems, developing comprehensive service guarantee policies and establishing dedicated service recovery teams to transform service failures into trust-building opportunities. Originality/value This study analyses customer behaviours by incorporating the service recovery paradox and service-dominant logic theory to provide new insights into how e-service attributes and recovery processes influence e-satisfaction and e-advocacy.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.