An Analysis of Online Review Helpfulness that Integrates Content and Function Words ─ An Application to Online Reviews on Amazon.com

• Published in: Journal of Marketing Science Vol. 28; no. 1; p. 49
• Format: Journal Article
• Language: English
• Published: Japan Institute of Marketing Science 2020
• ISSN: 2187-4220; 2187-8315
• DOI: 10.11295/marketingscience.202006

The helpfulness of online reviews can be driven by several factors: review attributes, reviewerattributes, review contents, review sentiments, and review language styles, among others. Althoughprevious studies identified the importance of these factors, most of them only concentrated on a few ofthe factors and did not take a holistic view. In the field of computer science, researchers alwaysfocused on the review content and sentiment by mining content words, and neglected language stylesdetermined by function words. This article aims to extend existing research on the classification ofonline reviews and their helpfulness by taking all of these factors into account. A theoreticalframework that integrates（ 1） reviewer attribute,（ 2） review attribute,（ 3） review content,（ 4） reviewsentiment, and （5） review language style is proposed. Based on the framework, this study analyzedonline reviews on iPads that are written in English and posted on Amazon.com. For the analysis ofreview content, topic modeling was applied through the latent Dirichlet allocation（ LDA） technique.For the analysis of review sentiment and language styles, a text processing software named LIWC（Linguistic Inquiry and Word Count） was used. A set of Poisson regression analysis was conducted,taking the number of “helpful” votes to the message as a dependent variable. Since significantrelationships with the five factors are obtained, the effectiveness of the proposed frameworkintegrating these was confirmed. This integrated view uncovers novel insights. Theoretical andpractical implications are also discussed.