Smart Detection of Fake Job Post Using Albert + Xgboost Intelligence
Year: 2025
Type: article
Abstract: The increase of false job adverts across the internet has resulted in a spike in employment fraud which greatly endangers a job seekers finances as well as their identity. Many people fail to identify which job listings are authentic and which ones are fake, making them an easy target for fraudsters. This project proposes a solution in the form of a Fake Job Post Detection System which applies ALBERT for the extraction of deep contextual features from the job descriptions and XGBoost for categorizing the posts into real or fake. It is trained on a Kaggle dataset containing labeled job postings with details such as job title, company name, and description. The system takes user-inputted job details and identifies patterns associated with fake job listings. ALBERT extracts linguistic features and XGBoost makes predictions based on the extracted features. To build trust Explainable?AI (XAI) is incorporated wherein the user can comprehend the decision-making process. This system not?only assists job seekers in spotting fraudulent job advertisements but also encourages a safer job-seeking experience.
Author: Mrs. Siriginedi Sai Brundavanam1, Malleswari Gujjula2, Raavi Samba Siva Reddy3, Yarra Harika4, Dhupati Srinivasu5
Language: English
Topic: Spam and Phishing Detection
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7106289744
FWCI:
Cites:
Cited by:
Related to: