Stay On-Topic: Generating Context-specific Fake Restaurant Reviews

TL;DR

This paper introduces a neural machine translation approach to generate context-specific fake restaurant reviews that are highly undetectable, surpassing previous methods in evasion success, while also developing effective detection tools.

Contribution

It presents a novel NMT-based method for generating more contextually accurate fake reviews and demonstrates its superior evasion capabilities over existing techniques.

Findings

Generated reviews have near-optimal undetectability (F-score 47%)

The method evades detection more effectively than state-of-the-art (average evasion 3.2/4 vs 1.5/4)

Detection tools achieve 97% accuracy in classifying fake reviews

Abstract

Automatically generated fake restaurant reviews are a threat to online review systems. Recent research has shown that users have difficulties in detecting machine-generated fake reviews hiding among real restaurant reviews. The method used in this work (char-LSTM ) has one drawback: it has difficulties staying in context, i.e. when it generates a review for specific target entity, the resulting review may contain phrases that are unrelated to the target, thus increasing its detectability. In this work, we present and evaluate a more sophisticated technique based on neural machine translation (NMT) with which we can generate reviews that stay on-topic. We test multiple variants of our technique using native English speakers on Amazon Mechanical Turk. We demonstrate that reviews generated by the best variant have almost optimal undetectability (class-averaged F-score 47%). We conduct a user study with skeptical users and show that our method evades detection more frequently compared to the state-of-the-art (average evasion 3.2/4 vs 1.5/4) with statistical significance, at level {\alpha} = 1% (Section 4.3). We develop very effective detection tools and reach average F-score of 97% in classifying these. Although fake reviews are very effective in fooling people, effective automatic detection is still feasible.