Chapter 6: Appendix C: Reviews that get filtered
We combined the filtered and test datasets, and used a binary logistic regression to examine properties that distinguish filtered reviews. Prior literature has identified low review count, low word count, and rating extremity as correlates of reviews likely to be fake or otherwise untrustworthy (Luca and Zervas 2013; Mayzlin et al. 2012; Pan and Zhang 2011). Intuitively, a short review from a consumer with no history that gives an extreme rating is more likely to be dishonest or incompetent, and hence, untrustworthy. Here extremity was measured by two dummy variables, picking out ratings of ‘1’ and ‘5’ respectively. We also tested friend count and lifetime totals of feedback. Because the zero level may be meaningful in its own right (that is, the difference between having one friend versus none may matter more, than the difference between having ten and 20 friends), both friend count and lifetime feedback were split into zero/any, and both the binary and intact counts (as logs) were tested.
You are not authenticated to view the full text of this chapter or article.
Elgaronline requires a subscription or purchase to access the full text of books or journals. Please login through your library system or with your personal username and password on the homepage.
Non-subscribers can freely search the site, view abstracts/ extracts and download selected front matter and introductory chapters for personal use.
Your library may not have purchased all subject areas. If you are authenticated and think you should have access to this title, please contact your librarian.