An Intelligent System for Identifying Fake Job Ads Using CNN-BiGRU and CNN-BiLSTM

In today’s digital age, online job portals have become a popular platform for job seekers to find employment opportunities, but the prevalence of fraudulent job ads has made it increasingly difficult for job seekers to identify genuine job openings, and a very few models can predict the accurate results. To tackle this issue, our study employs deep learning methods, including CNN–BiGRU (Bidirectional Gated Recurrent Units) and CNN-BiLSTM (Bidirectional Long Short-Term Memory) in conjugation with Natural Language Processing (NLP) techniques like tokenization and count vectorization. To train our model, we collected data from Google Dataset Search. Upon extensive testing and fine-tuning, we discovered that CNN-BiGRU and CNN-BiLSTM were highly proficient at distinguishing between authentic and fraudulent job ads. Our model demonstrated a high degree of reliability in identifying fake job posts, achieving an accuracy rate of 97% in eliminating fraudulent job advertisements, a significant improvement of +5% in accuracy, enabling us to provide job seekers with a safer and more confident online platform experience, with far-reaching implications for development of fraud detection systems in various domains, including the Digital Employment Market, Government Agencies, Social Media Platforms, Research and Policy Development.