The effect of novel linguistic-based review features on review helpfulness through information ecosystem and ELM theories: Heterogeneity analysis across platforms

Abstract

Although online review helpfulness has been extensively discussed, examining it at the platform level can still yield new insights. Drawing on ELM and information ecosystem theories, this study identifies heterogeneity in review features and their impact on helpfulness across platforms through a multimethod analysis of 82,130 reviews on JD and TikTok. Econometric analysis revealed that reviews on mature platforms contain richer objective content, more diverse language styles, and stronger semantic associations. In terms of content, objective content diversity positively affects helpfulness on emerging platforms, while it has the opposite effect on mature platforms. Negative sentiment significantly affects helpfulness only on mature platforms, and positive sentiment has no significant effect on either platform. In terms of language style, the analysis indicated that language style diversity positively impacts the helpfulness of emerging platforms. However, four specific styles (figurative, comparative, interrogative and exaggerative) negatively affect helpfulness on emerging platforms, with only comparative style having a significant negative effect on mature platforms. In terms of semantic association, the results show a more substantial positive impact on emerging platforms. Machine learning-based performance analysis corroborates the core findings of the econometric analysis. This study provides novel findings to the existing literature and provides managerial implications for different platforms.