Large-Scale Cross-Category Analysis of Consumer Review Content on Sales Conversion Leveraging Deep Learning
Xiao Liu, Dokyun Lee, and Kannan Srinivasan, 2018, 18-117-07
What content in product reviews matter? What content do consumers care about reading when on a journey to purchase a product online?
Xiao Liu, Dokyun Lee, and Kannan Srinivasan study the role of review content in consumer purchase journeys by leveraging a unique, granular-level dataset that tracks individual consumers’ entire decision journeys, including review reading, search, and purchase. This allows for discovery of what (types of products), for whom (how many consumers), and where (on which device) consumers read review content, as well as what dimensions of review content have a causal impact on conversion.
The authors approach the problem leveraging a theory-driven quality and price content dimension from more than 500,000 reviews spanning nearly 600 product categories. After providing the topology and the state of consumer review-reading behaviors, the study quantifies the causal impact of content information of read reviews on sale. To content tag theory-driven quality and price content dimensions, the authors utilize a variety of deep learning text-mining techniques to both scale and increase accuracy. To achieve causality, the authors rely on regression discontinuity in time design.
They show that aesthetics and price content in the reviews significantly affect conversion across almost all product categories. Review content information has a higher impact on sales when the average rating is higher and the variance of ratings is lower. Consumers depend more on review content when the market is more competitive, immature, or when brand information is not easily accessible. A counterfactual simulation suggests that reordering reviews based on content can have the same effect as a 1.6% price cut for boosting conversion.
The results can assist managers in multiple ways. First, managers can implement the deep learning models, as demonstrated, to automatically extract price and quality information from reviews of any product category for further uses. Second, based on the finding regarding the relative importance of review content dimensions, managers can incorporate reviews as a new marketing mix, by refining the ranking and information presentation algorithms to provide the most relevant reviews to consumers. Third, managers can collect real-time information about the consumer purchase journey, including device and reviews read, to predict final conversion more accurately.
Xiao Liu is Assistant Professor of Marketing, Stern School of Business, New York University. Dokyun Lee is Assistant Professor of Business Analytics and Kannan Srinivasan is H.J. Heinz II Professor of Management, Marketing and Business Technologies, both at Tepper School of Business, Carnegie Mellon University.
The authors gratefully acknowledge financial support from the Marketing Science Institute (https://www.msi.org) and NET Institute (www.netinst.org).
Making Words Speak: Leveraging Consumer Insights from Online Review Text to Improve Service Quality
Andrea Ordanini, Raji Srinivasan, and Anastasia Nanni (2018) [Report]
- Corporate: FREE
- Academic: FREE
- Subscribers: FREE
- Public: $18.00
3 WAYS to GET CONNECTED
Employees of MSI Member Companies enjoy the benefits of complete online access to content, member conferences and networking with the MSI community.
Qualified academics benefit from a relationship with MSI through access to msi.org, conferences and research opportunities.
The public is invited to enjoy partial access to msi.org content, a free e-newsletter, selected reports and more.