Abstract
With the profusion of social media, users increasingly browse through hotel reviews posted in websites such as TripAdvisor.com or Expedia.com to make a booking. Concurrently, contributing deceptive reviews to unduly applaud hotels is fast becoming a well-established e-business malpractice. Therefore, analyzing differences between genuine and deceptive reviews has become a pressing issue. Though such differences are generally difficult to detect, there could be telltale signs in terms of readability, genre, and writing style of reviews. This paper thus conducts a linguistic analysis to investigate the extent to which readability, genre, and writing style could predict review authenticity. Drawing data from a publicly available secondary dataset that includes 400 genuine and 400 deceptive reviews for hotels, results indicate that readability and writing style could be significant predictors of review authenticity. With respect to review genre however, differences between genuine and deceptive reviews appeared largely blurred. The implications of the findings are discussed. Finally, the paper concludes with notes on limitations and future research directions.
Original language | English |
---|---|
Title of host publication | Proceedings of 2014 Science and Information Conference, SAI 2014 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 938-942 |
Number of pages | 5 |
ISBN (Electronic) | 9780989319317 |
DOIs | |
Publication status | Published - Oct 7 2014 |
Externally published | Yes |
Event | 2014 Science and Information Conference, SAI 2014 - London, United Kingdom Duration: Aug 27 2014 → Aug 29 2014 |
Publication series
Name | Proceedings of 2014 Science and Information Conference, SAI 2014 |
---|
Conference
Conference | 2014 Science and Information Conference, SAI 2014 |
---|---|
Country/Territory | United Kingdom |
City | London |
Period | 8/27/14 → 8/29/14 |
Bibliographical note
Publisher Copyright:© 2014 The Science and Information (SAI) Organization.
ASJC Scopus Subject Areas
- Information Systems
Keywords
- e-business
- linguistic analysis
- opinion spam
- user-generated content