Study on the method of identifying opinion leaders based on online customer reviews

摘要

The deepening adoption of Web2.0 technology causes more and more users to publish reviews on the web about products, services, brands or business, and the online customer reviews (OCR) greatly influence customers' purchasing decisions and corporate reputations. Therefore, it has significant value for enterprises to identify the opinion leaders of OCR. This study proposes a RFMS model to measure the influential power of OCR publisher combining RFM model and automatically measuring method of sentiment words, then identify opinion leaders by applying artificial neural network, finally assess the validity of identifying results based on the degree of centrality. This research analysis the online reviews of dianping.com, and make a data verification of the proposed method. Results show that the proposed method in this paper can accurately identify opinion leaders.