What are they saying? A methodology for extracting information from online reviews

Wael Jabr, Kai Zhao, Yichen Cheng, Sanjay Srivastava

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

The growth of online shopping has made online reviews a critical source of information for consumers. There are, however, lots of them, in the thousands and sometimes hundreds of thousands for a single product. And these reviews keep arriving persistently over time, be it the ones that rate the product highly or the ones that rate it less favorably. With the information in those reviews publicly available online, the post-purchase experiences of millions of customers are literally put on display. Through a deep dive into the content of reviews over time and across satisfaction levels, this paper studies the text of online reviews through the lens of information revelation. Using a novel methodology, we deconstruct reviews into the aspects they discuss, the importance they associate with those aspects and the satisfaction they express towards them. We then apply this methodology to a large review dataset from Amazon. This allows us to evaluate the temporal evolution of user satisfaction with these aspects at a granular level. We find that aspects being discussed do not change over the half-life of products. We also find that user satisfaction with these aspects are very different when comparing favorable reviews to less favorable ones. Somewhat surprisingly, aspects that generate a strong positive satisfaction for positive reviews have a neutral or muted mention in negative reviews. Our work has major implications to a variety of stakeholders; the platform hosting the reviews, the sellers and the customers.

Original languageEnglish (US)
Title of host publicationInternational Conference on Information Systems 2018, ICIS 2018
PublisherAssociation for Information Systems
ISBN (Electronic)9780996683173
StatePublished - 2018
Event39th International Conference on Information Systems, ICIS 2018 - San Francisco, United States
Duration: Dec 13 2018Dec 16 2018

Publication series

NameInternational Conference on Information Systems 2018, ICIS 2018

Conference

Conference39th International Conference on Information Systems, ICIS 2018
CountryUnited States
CitySan Francisco
Period12/13/1812/16/18

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Statistics, Probability and Uncertainty
  • Library and Information Sciences
  • Applied Mathematics

Fingerprint Dive into the research topics of 'What are they saying? A methodology for extracting information from online reviews'. Together they form a unique fingerprint.

Cite this