Exploring the effects of consumers’ trust : a predictive model for satisfying buyers’ expectations based on sellers’ behaviour in the marketplace

Al Sheikh, SS, Shaalan, K and Meziane, F ORCID: https://orcid.org/0000-0001-9811-6914 2019, 'Exploring the effects of consumers’ trust : a predictive model for satisfying buyers’ expectations based on sellers’ behaviour in the marketplace' , IEEE Access, 7 (1) , pp. 73357-73372.

PDF (Accepted proof) - Published Version
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview


In recent years, Consumer-to-Consumer (C2C) marketplaces have become very popular among Internet users. However, compared to traditional Business-to-Consumer (B2C) stores, most modern C2C marketplaces are reported to be associated with stronger negative sentiments among consumers. These negative sentiments arise from the inability of sellers to meet certain buyers’ expectations and are linked to the low trust relationship among sellers and buyers in C2C marketplaces. The growth of these negative emotions might jeopardize buyers’ decisions to opt for C2C marketplaces in their future purchase intentions. In the present study, we extend the definition of trust as an emotion to cover the digital world and demonstrate the trust model currently used by most online stores. Based on the buyer’s behaviour in the C2C marketplace, we propose a conceptual framework to predict trust between the buyer and the seller. Given that C2C marketplaces are rich sources of data for trust mining and sentiment analysis, we perform text mining on Airbnb to predict the trust level in host descriptions of offered facilities. The data are acquired from the US city of Ashville, Alabama, and Manchester in the UK. The results of the analysis demonstrate that guest negative feedback in reviews are high when the description of the host’s property has the emotion of joy only. By contrast, guest negative sentiments in reviews are at a minimum when the host’s sentiment has mixed emotions (e.g., joy and fear).

Item Type: Article
Schools: Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre
Journal or Publication Title: IEEE Access
Publisher: IEEE
ISSN: 2169-3536
Related URLs:
Depositing User: Prof Farid Meziane
Date Deposited: 28 May 2019 11:36
Last Modified: 16 Feb 2022 02:08
URI: https://usir.salford.ac.uk/id/eprint/51433

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)


Downloads per month over past year