• R. SANDHYA
• N. VINAY KUMAR
• B. PRAVALLIKA
• MR. G. VIJAY KUMAR

In modern times, the development in the field of industry and technology has opened a huge opportunity for new and diverse jobs for job seekers. With the help of advertisements of these job offers, job seekers find out their options depending on their time, qualification, experience, suitability, etc. The recruitment process is now influenced by the power of the internet and social media. Since the successful completion of a recruitment process is dependent on its advertisement, the impact of social media over this is tremendous. Social media and advertisements in electronic media have created newer and newer opportunities to share job details. However, the rapid growth of opportunities to share job ads has increased the percentage of fraudulent job postings, which causes harassment to job seekers. People lack interest in new job postings due to concerns about the security and consistency of their personal, academic, and professional information. Thus, the true motive of valid job postings through social and electronic media faces an extremely hard challenge to attain people’s belief and reliability. Technologies are around us to make our lives easy and developed but not to create an unsecured environment for professional life. If job ads can be filtered properly to predict false job ads, this would be a great advancement for recruiting new employees. Therefore, this project proposes to use different data mining techniques and classification algorithms like K-nearest neighbor, decision tree, support vector machine, naive Bayes classifier, random forest classifier, and multi-layer perceptron to predict if a job advertisement is real or fraudulent. We have experimented on the Employment Scam Aegean Dataset (EMSCAD) containing 18000 samples. Deep neural network as a classifier performs great for this classification task. We have used three dense layers for this deep neural network classifier. The trained classifier shows approximately 98% classification accuracy (DNN) to predict a fraudulent job ad.

Prediction of Fake Job Ad using NLP-based Multilayer Perceptron

"Prediction of Fake Job Ad using NLP-based Multilayer Perceptron", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.d285-d290, April-2024, Available :http://www.jetir.org/papers/JETIR2404340.pdf

"Prediction of Fake Job Ad using NLP-based Multilayer Perceptron", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppd285-d290, April-2024, Available at : http://www.jetir.org/papers/JETIR2404340.pdf