Authors : G. Shravaneshwari; M. M. Harshitha; Dr. Girish Kumar D.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/ye25ubcf

Scribd : https://tinyurl.com/bdwt2j4d

DOI : https://doi.org/10.38124/ijisrt/26apr682

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : AI and Natural Language Processing (NLP) have evolved in recent years, forever changing online recruitment platforms. Whilst these technologies have made strides in accessibility and efficiency, they have also paved the way for a rapid rise in job-related fraud, with fake job postings used as deceitful means to harvest sensitive personally identifiable information or extort money from resolute job seekers. This paper presents "Recruit Shield," a state-of-the-art system that detects fraudulent job postings using machine learning techniques and NLP-based text analysis with a secure web application. The proposed system comprises of multiple classifiers(including Logistic Regression, Random Forest, Naive Bayes and Support Vector Tools to Social Machines that make predictions whether a job is real or fake Users can simply input relevant details related to their job and are provided with prediction probabilities alongside a search history through the user-facing interface supported by Streamlit, while an administrative dashboard offers deep analytical insights. Animated results also show a detection accuracy of up to 98.55%, as well as good security features, gaining abilities from current web tools like for checking input validation and encrypting authentication. By demonstrating the potential benefits of combining supervised machine learning techniques and contemporary web technologies, the results underline one possible path to improving security of digital recruitment systems.

Keywords : Machine Learning, Fake Job Detection, Natural Language Processing (NLP), Stream Lit, Random Forest, Cybersecurity, Online Recruitment, TF-IDF.

References :

1. A. Kumar, S. Gupta, and R. Singh, "Enhanced Fake Job Detection using BERT and Ensemble Learning Techniques," IEEE Access, 2024.
2. P. Sharma, N. K. Trivedi, and V. K. Mishra, "A Robust Framework for Detecting Fraudulent Job Postings Using Natural Language Processing," in Proc. Int. Conf. on Computing and Communication Systems (I3CS), IEEE, 2023, pp. 1–6.
3. M. A. Al-Garadi, K. D. Varathan, and S. D. Ravana, "Online Recruitment Fraud Detection: A Systematic Review," IEEE Trans. Comput. Soc. Syst., vol. 10, no. 2, pp. 678–692, 2023.
4. R. Singh, T. Choudhury, and S. Kumar, "Recruit Fraud Detection System using Machine Learning and TF-IDF," in Int. Conf. on Artificial Intelligence and Speech Technology (AIST), 2023, pp. 210–218.
5. V. B. N. Kumar and R. S. Reddy, "Identification of Fake Job Postings using Supervised Machine Learning Algorithms," in 2nd Int. Conf. on Artificial Intelligence and Signal Processing (AISP), IEEE, 2022, pp. 1–5.
6. S. Ranade, S. Kadam, and P. Deshmukh, "Fake Job Posting Detection using Natural Language Processing," Int. J. Eng. Res. Technol. (IJERT), vol. 11, no. 5, pp. 45–50, 2022.
7. S. Habib, N. Alsaedi, and S. Al-Rubaian, "Job Scam Detection Using Machine Learning: A Comparative Analysis," IEEE Access, vol. 9, pp. 12345–12356, 2021.
8. M. Umer, M. Ashraf, and A. Mehmood, "A Hybrid Deep Learning Approach for Fake Job Detection," Expert Syst. Appl., vol. 180, p. 115123, 2021.
9. A. H. Khan, M. A. Khan, and S. Abbas, "Online Recruitment Fraud Detection using NLP and Machine Learning," J. Ambient Intell. Humanized Comput., vol. 12, no. 10, pp. 1–12, 2021.
10. I. K. Dutta and M. Bandyopadhyay, "Fake Job Posting Detection using Machine Learning," in Int. Conf. on Computing, Communication and Networking Technologies (ICCCNT), IEEE, 2020, pp. 1–6.