Complementing human effort in online reviews: A deep learning approach to automatic content generation and review synthesis |
| |
| Affiliation: | 1. Department of Computer Science, Dartmouth College, Hanover, NH 03755, United States;2. 100 Tuck Hall, Tuck School of Business at Dartmouth, Dartmouth College, Hanover, NH 03755, United States;3. School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, IN 47405, United States;4. Departments of Computer Science and Department of Mathematics, The Santa Fe Institute, Santa Fe, NM 87501, United States;5. Dartmouth College, Hanover, NH 03755, United States;1. National Chair, Restore the Fourth, United States;2. Sloan Distinguished Professor of Management, MIT, United States;1. Drexel University, USA;2. INSEAD, France;1. Professor of Marketing and Sarah Kenan Graham Scholar at the University of North Carolina at Chapel Hill, USA;2. Research Professor of marketing department at Tilburg University, the Netherlands;3. Professor of Marketing at KU Leuven, Belgium;4. Fellow at the Emerging Markets Institute, INSEAD, Singapore;5. Lee Kong Chian Professor of Marketing, and Director of Retail Centre of Excellence, at the Lee Kong Chian School of Business, Singapore Management University, Singapore;1. IESE Business School, University of Navarra, Barcelona 08034, Spain;2. Imperial College of London, London SW7 2AZ, United Kingdom;3. HEC Paris, 78350 Jouy-en-Josas, France;4. Adele and Norman Barron Professor of Management, Questrom School of Business, Boston University, Boston, MA 02215, United States;5. D’Amore-McKim School of Business, Northeastern University, Boston, MA 02115, United States;6. BI Norwegian Business School, Oslo, Norway;1. The London School of Economics, United Kingdom;2. The McCombs School of Business, University of Texas at Austin, United States;3. Southeast University, Nanjing, China |
| |
| 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 processing 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. |
| |
| Keywords: | Online reviews Artificial intelligence Machine learning Wine reviews Review synthesis Automation Deep learning |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
