Investigation of Deep Learning Approaches for Online Recruitment Fraud Detection

Modern companies increasingly rely on digital platforms to recruit new employees and streamline the hiring process. However, the surge in online job postings has led to a rise in fraudulent advertisements, where scammers exploit job seekers for financial gain. Online recruitment fraud has become a significant concern in cybercrime, necessitating effective detection mechanisms to combat fake job listings. While traditional machine learning and deep learning models have been employed for this task, this research explores the effectiveness of two transformer-based deep learning models—Bidirectional Encoder Representations from Transformers (BERT) and the Robustly Optimized BERT Pretraining Approach (RoBERTa) in accurately identifying fraudulent job postings.