Product ranking through fusing the wisdom of consumers extracted from online reviews on multiple platforms

Ranking products based on online reviews has become an important measure to support consumers' purchasing decisions. How to make an effective decision considering online review information from different e-commerce platforms is a challenge. In this regard, this study introduces a large-scale group decision-making (LSGDM) method to assist users in making purchasing decisions by extracting the collective wisdom of reviewers across different platforms. First, we use the lexical analysis system, term frequency-inverse document frequency algorithm, and sentiment dictionary to process online review data and obtain product attributes, the weights of attributes, and sentiment scores of reviews, respectively. The weights of platforms are determined using an integrated method that considers the characteristics of each platform. Afterwards, we present an LSGDM method to achieve the coordination of the wisdom of reviewers. We collect online reviews of four mobile phones from Tmall, JD and Suning, providing experimental analyses to demonstrate the applicability of our proposed method.