Fact or Factitious? Contextualized Opinion Spam Detection

TL;DR

This paper compares various methods for detecting fake online reviews, highlighting the effectiveness of contextualized embeddings and introducing a fine-tuned approach that advances the state of the art in opinion spam detection.

Contribution

It provides an analytic comparison of existing techniques and introduces a novel approach using fine-tuned contextualized embeddings for improved fake review detection.

Findings

Contextualized embeddings show strong potential for fake review detection.

Fine-tuning embeddings improves detection accuracy.

The study establishes a foundation for future research in opinion spam detection.

Abstract

In this paper we perform an analytic comparison of a number of techniques used to detect fake and deceptive online reviews. We apply a number machine learning approaches found to be effective, and introduce our own approach by fine-tuning state of the art contextualised embeddings. The results we obtain show the potential of contextualised embeddings for fake review detection, and lay the groundwork for future research in this area.