Fake Job Postings Detection: Deep Learning Approach for Fraudulent Employment Advertisements

The study's results demonstrate that combining textual semantics with categorical features in a unified architecture yields a highly effective fraud detection system. The CNN's ability to learn spatial hierarchies of features from text, such as phrases and sentence structures commonly found in deceptive advertisements, is the primary driver of its superior performance. This suggests that fraudulent postings, despite mimicking legitimate ones, often contain subtle linguistic artifacts that can be automatically learned by such models. Furthermore, the success of the real-time web application underscores the viability of deploying such systems in production. The ability to provide instantaneous feedback to users is crucial for trust and usability, making this system a practical tool for integration into existing job portals or for use as a standalone verification service.

[1]     S. Vidros, C. Kolias, G. Kambourakis, and L. Akil, "Automatic detection of online recruitment fraud: A machine learning approach," in Proc. 2017 IEEE Int. Conf. Inf. Intell. Syst. Appl. (IISA), 2017, pp. 1-6. [2]    D. Dutta and S. Bandyopadhyay, "Single vs. Ensemble Machine Learning Models for Fake Job Posting Detection," in Proc. Int. Conf. Adv. Comput. Commun. Eng. (ICACCE), 2020, pp. 1-5. [3]  V. Lokku, R. R. Reddy, and P. S. R. Ch, "Detection of Fake Job Postings using Machine Learning," in Proc. Int. Conf. Emerg. Trends Inf. Technol. Eng. (ICETITE), 2021, pp. 1-4. [4]  A. Nasser, R. A. Saeed, and S. A. Alsharif, "An approach for detecting fake job postings using artificial neural network," Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 8, pp. 297-304, 2021. [5]  M. S. Akram, M. N. Akbar, and S. A. Khan, "An Enhanced Deep Learning Framework for Fake Job Posting Detection Using BERT and RoBERTa," IEEE Access, vol. 12, pp. 24312-24328, 2024. [6]   F. Habiba, A. G. S. Al-Ghamdi, and A. A. Darwish, "A Comparative Study of Machine Learning and Deep Learning Techniques for Fake Job Posting Detection," in Proc. 2021 Int. Conf. Data Min. Mach. Learn. (DMML), 2021, pp. 45-51. [7]      Kaggle. (2017). Fake Job Postings Dataset. [Online]. Available: https://www.kaggle.com/datasets/shivamb/real-or-fake-fake-jobposting-prediction [8]    D.-H. Vu, K. Nguyen, K. T. Tran, B. Vo, and T. Le, "Improving fake job description detection using deep learning-based NLP techniques," J. Inf. Telecommun., vol. 9, no. 1, pp. 113–125, 2025. [9]   S. S. Suhas Sanisetty et al., "Comprehensive Approach to Fraudulent Job Post Detection Using Machine Learning and BERT Models," in Proc. 2025 4th Int. Conf. on Distributed Computing and Electrical Circuits and Electronics (ICDCECE), Ballari, India, 2025, pp. 1–6. [10]    "Fraud-BERT: transformer based context aware online recruitment fraud detection," Discover Computing, vol. 28, no. 9, 2025.