In authority, or peers we trust? Reviews and recommendations in social commerce

ABSTRACT

Social commerce is an emergent business model where user-generated content is a valuable source of information that minimises the risk and ambiguity surrounding online purchase decisions. This study examines the user-generated content represented by reviews and recommendations (electronic word of mouth or eWOM) by contrasting customer (peer) vs. authority (expert) generated eWOM, from a product buying criteria perspective. Using five consumer healthcare wearable products as a benchmark, customer reviews from Amazon.com were analysed and compared with expert reviews and recommendations from Consumer Reports using machine learning techniques such as Latent Dirichlet Allocation (LDA) topic modelling, logistic regression, multinomial naïve Bayes, random forest and support vector machines. The findings suggest that expert reviews and recommendations remain product-centric and are not attuned to shifts in customer buying patterns, thus missing out on important product context-based usage and evaluation criteria such as operational, personal, and environmental. Considering these results, the authors discuss implications for managers and researchers, and future research directions.

KEYWORDS:

• Social commerce
• eWOM
• machine learning
• data mining
• decision making

Disclosure statement

No potential conflict of interest was reported by the authors.