Wharton Customer Analytics
Research Paper Series
On the Spillover Effects of Online Product Reviews on Purchases: Evidence from Clickstream Data
We analyze the spillover effects of the online reviews of other co-visited products on the purchases of a focal product using clickstream data from a large retailer. Drawing upon signaling theory, as online reviews serve as signals, the proposed spillover effects are moderated by: (a) whether the related (co-visited) products are complementary or substitutive, (b) the choice of media channel (mobile or PC) used, (c) whether the related products are from the same or a different brand, and (d) consumer experience and (e) the variance of the review ratings. To identify complementary and substitutive products, we develop supervised machine-learning models based on product characteristics, such as product category and brand, and novel text-based similarity measures; to train and validate the machine-learning models, we use product-pair labels from Amazon Mechanical Turk. Our results show that the mean rating of substitutive products has a negative effect on the purchasing of the focal product, while that of complementary products has a positive effect on the focal product purchases. Interestingly, the magnitude of the spillover effects of the mean ratings of co-visited (substitutive and complementary) products is larger than the effects on the focal product, especially for complementary products. The spillover effect of ratings is stronger for consumers who use mobile devices versus PCs. We find that the negative effect of the mean ratings of substitutive products across different brands in the purchasing of a focal product is significantly higher than those within the same brand. Lastly, we find that the effect of the mean ratings is stronger for less-experienced consumers and for ratings with lower variance. We conclude with theoretical, managerial, and design implications on leveraging the spillover effect of the online product reviews of related products to encourage online purchases.
Keywords: Online Product Reviews, Substitutive Products, Complementary Products, Brand Spillover, WOM Spillover, Topic Modeling, Machine Learning