A Domain-Independent Holistic Approach to Deception Detection

TL;DR

This paper presents a deep learning-based, domain-independent approach to deception detection in text, achieving state-of-the-art accuracy across various types of deceptive content and revealing potential universal patterns of deception.

Contribution

It introduces a novel domain-independent deception detection method that outperforms existing models and explores the universality of deceptive writing styles across domains.

Findings

Achieved 93.42% accuracy and 93.22% F1-score on benchmark datasets.

Domain-independent training captures subtle deception cues.

Universal deception patterns may exist across different text domains.

Abstract

The deception in the text can be of different forms in different domains, including fake news, rumor tweets, and spam emails. Irrespective of the domain, the main intent of the deceptive text is to deceit the reader. Although domain-specific deception detection exists, domain-independent deception detection can provide a holistic picture, which can be crucial to understand how deception occurs in the text. In this paper, we detect deception in a domain-independent setting using deep learning architectures. Our method outperforms the State-of-the-Art (SOTA) performance of most benchmark datasets with an overall accuracy of 93.42% and F1-Score of 93.22%. The domain-independent training allows us to capture subtler nuances of deceptive writing style. Furthermore, we analyze how much in-domain data may be helpful to accurately detect deception, especially for the cases where data may not be readily available to train. Our results and analysis indicate that there may be a universal pattern of deception lying in-between the text independent of the domain, which can create a novel area of research and open up new avenues in the field of deception detection.