Distributional Footprints of Deceptive Product Reviews

Authors

  • Song Feng Stony Brook University
  • Longfei Xing Stony Brook University
  • Anupam Gogar Stony Brook University
  • Yejin Choi Stony Brook University

DOI:

https://doi.org/10.1609/icwsm.v6i1.14275

Keywords:

opinion analysis, deception detection, spam detection, text mining

Abstract

This paper postulates that there are natural distributions of opinions in product reviews. In particular, we hypothesize that for a given domain, there is a set of representative distributions of review rating scores. A deceptive business entity that hires people to write fake reviews will necessarily distort its distribution of review scores, leaving distributional footprints behind. In order to validate this hypothesis, we introduce strategies to create dataset with pseudo-gold standard that is labeled automatically based on different types of distributional footprints. A range of experiments confirm the hypothesized connection between the distributional anomaly and deceptive reviews. This study also provides novel quantitative insights into the characteristics of natural distributions of opinions in the TripAdvisor hotel review and the Amazon product review domains.

Downloads

Published

2021-08-03

How to Cite

Feng, S., Xing, L., Gogar, A., & Choi, Y. (2021). Distributional Footprints of Deceptive Product Reviews. Proceedings of the International AAAI Conference on Web and Social Media, 6(1), 98-105. https://doi.org/10.1609/icwsm.v6i1.14275