Home // ICDS 2014, The Eighth International Conference on Digital Society // View article

Sensitivity of Information Disclosed in Amazon Reviews

Authors:
Federica Fornaciari
Ranganathan Chandraskaren
Venkat Venkatakrishnan

Keywords: Privacy; Identity; Users-Generated Content; Sensitive Information; Natural Laguage Processing.

Abstract:
As online product reviews become ubiquitous, more individuals increasingly write and rely on them. In an effort to share their experiences and opinions about a product, do individuals share private and sensitive information online? This study addresses this critical issue by examining the extent of sensitive information disclosed in Amazon.com’s product reviews. We crawled Amazon.com and gathered all online reviews posted for six products that pertained to weight loss, anti-aging, sex-related, fragrance, baby care and electronic goods. This resulted in 3,485 reviews, which were textanalyzed and mined using Linguistic Inquiry and Word Count (LIWC) analysis. Then, data processed through LIWC were further analyzed through descriptive statistics and discriminant analysis. We found that Amazon’s reviewers disclose high levels of sensitive information in the following categories: family, humans, positive emotions, negative emotions, sadness, cognitive mechanisms, concerns related to work, achievements, leisure and money. Sensitive disclosure is also found to be a function of the type of reviewer and of the anonymization strategies adopted.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2014

Publication date: March 23, 2014

Published in: conference

ISSN: 2308-3956

ISBN: 978-1-61208-324-7

Location: Barcelona, Spain

Dates: from March 23, 2014 to March 27, 2014