How Online Reviews in a Year Predict Online Sales in the Next on + + A Panel Study of Hotels

Snehasish Banerjee, Stefanie Bonfield

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


This paper investigates how ratings, titles as well as descriptions of online reviews predict online sales. Using data from, and; a log-linear regression model was developed for a panel of 75 Asian hotels. The model explained 69.40% variance in the dependent variable for luxury hotels, 40.30% for budget hotels, and 38.80% for mid-scale hotels. In particular, title length was negatively related to sales for luxury and mid-scale hotels. The use of positive words in titles was positively related to sales for luxury hotels but had a negative association for budget hotels. Moreover, the use of positive (negative) words in descriptions was positively (negatively) related to sales for budget hotels.
Original languageEnglish
Title of host publication2019 5th International Conference on Information Management (ICIM)
Number of pages5
ISBN (Electronic)978-1-7281-3430-7
Publication statusPublished - 17 May 2019

Bibliographical note

©2019 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.


  • E-tourism
  • e-wom
  • online booking
  • online sales

Cite this