Unmasking Fraudulent Job Ads: A Critical Review of Machine Learning Techniques for Detecting Fake Jobs

Abstract

In today’s technology-driven world, where everything is just a few clicks away, online job postings have also increased clearly, allowing job seekers to apply for jobs via various online job portals. While this has made job hunting easier, the rise of fraudulent job advertisements has also augmented tremendously. Fraudulent job advertisements are created to deceive job seekers by extracting their personal information for several malicious purposes or monetary gain. It has become the need of the hour to protect job seekers from potential financial and identity theft by detecting these fraudulent job advertisements. This paper focuses on reviewing some
recent research on the detection of fraudulent job advertisements using machine learning approaches. In this paper, seven research papers were analyzed, focusing on the datasets, feature engineering techniques, machine learning algorithms, and evaluation metrics used to detect fraudulent job advertisements. The paper concludes by highlighting the current challenges and future directions for research in this area.