Online Deception Detection Refueled by Real World Data Collection

TL;DR

This paper introduces a new large-scale dataset of deceptive and truthful online reviews collected via social network analysis, enabling improved deception detection across diverse product domains.

Contribution

It presents a novel data collection method for realistic deception datasets and demonstrates the effectiveness of generalized features for cross-domain deception detection.

Findings

Generalized features like advertising speak and writing complexity improve detection accuracy.

Adding diverse deceptive reviews enhances model performance.

Reviewer writing styles vary significantly across deceptive reviewers.

Abstract

The lack of large realistic datasets presents a bottleneck in online deception detection studies. In this paper, we apply a data collection method based on social network analysis to quickly identify high-quality deceptive and truthful online reviews from Amazon. The dataset contains more than 10,000 deceptive reviews and is diverse in product domains and reviewers. Using this dataset, we explore effective general features for online deception detection that perform well across domains. We demonstrate that with generalized features - advertising speak and writing complexity scores - deception detection performance can be further improved by adding additional deceptive reviews from assorted domains in training. Finally, reviewer level evaluation gives an interesting insight into different deceptive reviewers' writing styles.