Analyzing the Online Word of Mouth Dynamics: A Novel Approach

Abstract

Nowadays, nearly all products and services generate WOM on social media but at least three challenges hinder the analysis of online WOM. First, WOM is usually unstructured data in various forms. However, the process of transforming unstructured data can generate many variables, increasing the need for dimension reduction. Second, WOM can be continuous or bursty, and it may change dramatically in a short period. Third, important events might trigger symmetric or asymmetric reactions in WOM across rivals. We introduce a new computationally efficient method—multi-view sequential canonical covariance analysis to solve these methodological challenges. This method attempts to solve the myriad WOM conversational dimensions, detect WOM dynamic trends, and examine the shared WOM across rivals. We illustrate the advantages of this new method using two empirical examples. This new method provides a novel insight into the online WOM dynamics and can contribute to a wide range of fields.

Keywords: Multi-view sequential canonical covariance analysis, canonical correlation analysis, online word-of-mouth dynamics, dimension reduction, social media