Events

This is a joint seminar organized by HKU Business School’s Marketing Area and Institute of Digital Economy & Innovation (IDEI).

Established in 2022, Institute of Digital Economy and Innovation (IDEI) aims to promote world-class interdisciplinary research and impactful community engagements on digital economy and innovation. Visit https://idei.hkubs.hku.hk/

Speaker

Professor Praveen Kopalle
Signal Companies’ Professor of Management
Professor of Marketing
Tuck School of Business
Dartmouth College

Abstract

Online product reviews are ubiquitous and helpful sources of information available to consumers for making purchase decisions. Consumers rely on both the quantitative aspects of reviews such as valence and volume as well as textual descriptions to learn about product quality and fit. In this paper we show how new achievements in natural language can provide an important assist for different kinds of review-related writing tasks. Working in the interesting context of wine reviews, we demonstrate that machines are capable of performing the critical marketing task of writing expert reviews directly from a fairly small amount of product attribute data (metadata). We conduct a kind of “Turing Test” to evaluate human response to our machine-written reviews and show strong support for the assertion that machines can write reviews that are indistinguishable from those written by experts. Rather than replacing the human review writer, we envision a workflow wherein machines take the metadata as inputs and generate a human readable review as a first draft of the review and thereby assist an expert reviewer in writing their review. We next modify and apply our machine-writing technology to show how machines can be used to write a synthesis of a set of product reviews. For this last application we work in the context of beer reviews (for which there is a large set of available reviews for each of a large number of products) and produce machine-written review syntheses that do a good job – measured again through human evaluation – of capturing the ideas expressed in the reviews of any given beer. For each of these applications, we adapt the Transformer neural net architecture. The work herein is broadly applicable in marketing, particularly in the context of online reviews. We close with suggestions for additional applications of our model and approach as well as other directions for future research.

Prof. Kopalle’s Bio

Praveen Kopalle is the Signal Companies’ Professor of Management and Professor of Marketing at the Tuck School of Business, Dartmouth College. Praveen received his Ph.D. from Columbia University, MBA from Indian Institute of Management, Bangalore, and B.E. from Osmania University.  Professor Kopalle’s teaching and research interests are in Marketing, Statistics, Pricing, new products/innovation, promotions, customer expectations, and e-commerce. Praveen serves as an Associate Editor at the Journal of Marketing and Journal of Retailing. In addition, he is on the editorial boards of Marketing Science, Journal of Marketing Research, Journal of Consumer Research, Marketing Letters, and Journal of Interactive Marketing. Praveen has won many awards including: 2011 Distinguished Alumni Award, Indian Institute of Management, Bangalore, India, 2015 Core Teaching Excellence Award, Winner, 2005 John Little Award etc. Praveen’s research has been published in many top-tier journals including Journal of Consumer Research, Journal of Marketing Research, Marketing Science, Management Science, International Journal of Research in Marketing, Strategic Management Journal, Organizational Behavior and Human Decision Processes, Journal of Retailing,Production and Operations Management, Journal of Product Innovation Management.  He has been invited to speak at over fifty universities and institutes worldwide.