Post-Purchase Trust in e-Commerce: A Theoretical Framework and a Text Mining-Based Assessment Method

Abstract

Post-purchase trust is formed after an online transaction is completed and the product or service is experienced. It influences consumers’ repurchase intention and the reputation of vendors. The aim of the current study was to deepen our understanding of post-purchase trust in e-Commerce and to develop a text mining-based assessment method by mining consumers’ online comments. By combining the expectancy-confirmation theory and product evaluation theory, this study proposes a comprehensive model of post-purchase trust encompassing consumers’ evaluation of product, delivery, service, and website. The model was verified by a survey involving 249 consumers. The results indicate that both product evaluation factors and transaction supporting factors have positive impacts on post-purchase trust. Based on this theoretical model, we proposed a text mining-based method to measure these factors through text-mining of consumers’ comments. To demonstrate the feasibility and benefits of the method, the method was applied to analyze 1,015,484 consumers’ comments on personal computer products from jd.com, a major Chinese e-Commerce website. The results suggest that the proposed method can provide practitioners with diagnostic suggestions to promote post-purchase trust and understand consumers better.

HIGHLIGHTS

• Integration of the consumers’ product evaluation model and expectation-confirmation theory is proposed to investigate post-purchase trust in e-commerce.

• The confirmation of delivery, service, website, and perceived value of products affect consumer satisfaction, thereby affect post-purchase trust.

• Perceived value is positively affected by perceived price and perceived quality, which can be increased by consumers’ evaluation of the appearance, authenticity, and brand reputation of the product.

• The proposed model can be used to design text mining-based tools to monitor important factors of post-purchase trust via text mining.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This study was supported by the National Natural Science Foundation of China (Project no. 71942005).

Notes on contributors

Zhaoyi Ma

Zhaoyi Ma is a PhD candidate in the Department of Industrial Engineering at Tsinghua University, Beijing, China. She received her bachelor’s degree from Tsinghua University in 2017. She has been working with Professor Qin Gao since then.

Qin Gao

Qin Gao received her PhD from Tsinghua University, Beijing, China. She is currently an associate professor in the Department of Industrial Engineering at Tsinghua University. Her main research includes user centered design, cognitive ergonomics, human–computer interaction, and decision-making.

Yue Chen

Yue Chen is an assistant professor in the School of Art Design and Media, East China University of Science and Technology. She received her PhD degree from Tsinghua University and worked with Prof. Qin Gao as a postdoctoral researcher. Her research interests include human factors, human-computer interaction, and social media.