Online reviews are an important information source in high-involvement durable-goods markets. However, limited empirical evidence has been accumulated on the extent to which online reviews explain monthly sales fluctuations at the individual vehicle-model level. Focusing on the Toyota RAV4, which ranked first in U.S. sales in 2024, this study constructs a 19-year monthly dataset integrating vehicle sales, online reviews, Google Trends, macroeconomic indicators, and exceptional market shocks. Grounded in the Heuristic–Systematic Model (HSM), the study estimates time-series regression models with standard errors robust to heteroskedasticity and autocorrelation. The results show that online review text signals exhibit a weak positive association with next-month sales even after controlling for macroeconomic variables, search volume, and calendar effects. In particular, the sentiment measure based on a simple aggregation of the latest 25 reviews was weakly significant in the final selected specification. By contrast, specifications that additionally weighted reviews by recency or helpfulness did not consistently improve explanatory power. Vehicle recommendation rate and some attribute-level rating specifications sometimes achieved comparable or even lower BIC values, although their coefficients were not statistically robust overall. Taken together, the findings suggest that online review signals may serve as supplementary indicators of demand in the context of high-involvement durable-goods purchases, but their explanatory power is limited. This study extends the online review literature to the individual vehicle level and offers managerial implications regarding which review signals automotive manufacturers and other stakeholders should prioritize as leading indicators of demand.
Lee et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: