Detection of opinion spam based on anomalous rating deviation

TL;DR

This paper introduces a lightweight rating deviation-based method for detecting opinion spam, focusing on rating anomalies without text analysis, achieving comparable accuracy to existing methods with less computational effort.

Contribution

The paper presents a novel, efficient approach using binomial regression to identify opinion spammers based solely on rating deviations from the majority opinion.

Findings

Successfully detects opinion spammers in real-world and synthetic data.

Achieves similar accuracy to state-of-the-art methods with reduced computational complexity.

Operates effectively without relying on review text analysis.

Abstract

The publication of fake reviews by parties with vested interests has become a severe problem for consumers who use online product reviews in their decision making. To counter this problem a number of methods for detecting these fake reviews, termed opinion spam, have been proposed. However, to date, many of these methods focus on analysis of review text, making them unsuitable for many review systems where accom-panying text is optional, or not possible. Moreover, these approaches are often computationally expensive, requiring extensive resources to handle text analysis over the scale of data typically involved. In this paper, we consider opinion spammers manipulation of average ratings for products, focusing on dif-ferences between spammer ratings and the majority opinion of honest reviewers. We propose a lightweight, effective method for detecting opinion spammers based on these differences. This method uses binomial regression to identify reviewers having an anomalous proportion of ratings that deviate from the majority opinion. Experiments on real-world and synthetic data show that our approach is able to successfully iden-tify opinion spammers. Comparison with the current state-of-the-art approach, also based only on ratings, shows that our method is able to achieve similar detection accuracy while removing the need for assump-tions regarding probabilities of spam and non-spam reviews and reducing the heavy computation required for learning.