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.

摘要

社交商务是一种新兴的商业模式，其中用户生成的内容是一种有价值的信息来源，可以最大限度地降低在线购买决策的风险和模糊性。本研究从产品购买标准的角度，通过对比客户（同行）与权威（专家）生成的 eWOM，检查以评论和推荐（电子口碑或 eWOM）为代表的用户生成的内容。以五款消费者保健可穿戴产品为基准，分析了来自 Amazon.com 的客户评论，并将其与来自消费者报告的专家评论和建议进行了比较，使用机器学习技术，例如 Latent Dirichlet Allocation (LDA) 主题建模、逻辑回归、多项式朴素贝叶斯、随机森林和支持向量机。调查结果表明，专家评论和建议仍然以产品为中心，并且不适应客户购买模式的转变，因此错过了重要的基于产品上下文的使用和评估标准，例如操作、个人和环境。考虑到这些结果，作者讨论了对管理者和研究人员的影响以及未来的研究方向。