SKK GSB Professor Nah Lee: Vertical versus Horizontal Variance in Online Reviews and Their Impact on Demand
- SKKGSB
- Hit11290
- 2022-08-25
Newly joined Marketing Professor Nah Lee's paper, "Vertical versus Horizontal Variance in Online Reviews and Their Impact on Demand," has been accepted for publication in the Journal of Marketing Research. Professor Lee received Ph.D. in Marketing from Duke University and her studies aim to understand how consumers process information in text reviews and how this information affects firm demand, decisions, and competition.
Abstract as below:
This paper examines the differential impact of variances in the quality and taste comments found in online customer reviews on firm sales. Using an analytic model, we show that although increased variance in consumer reviews about taste mismatch normally decreases subsequent demand, it can increase demand when mean ratings are low and/or quality variance is high. In contrast, increased variance in quality always decreases subsequent demand, although this effect is moderated by the amount of variance in tastes. Since these theoretical demand effects are predicated on the assumption that consumers can differentiate between the two sources of variation in ratings, we conduct a survey that demonstrates that subjects are indeed able to reliably distinguish quality from taste evaluations from two subsets of reviews of size 5,000 taken from our larger datasets of reviews for 4,305 restaurants and 3,460 hotels. We use these responses to construct sets of reviews that we use in a controlled laboratory experiment on restaurant choice, finding strong support for our theoretical predictions. These responses are also used to train classifiers using a bag-of-words model to predict the degree to which each review in the larger datasets relates to quality and/or taste allowing us to estimate the two types of review variances. Finally, we estimate the effects of these variances in overall ratings on establishment sales, again finding support for our theoretical results.
Keywords:
review variance, vertical and horizontal content, text analysis, machine learning, quality and taste variance, crowd-sourced data