Fake News Detection using Machine Learning

Abstract

The rise of the World Wide Web alongside the widespread adoption of social media platforms such as Facebook, Instagram, and Whatsapp has revolutionized the dissemination of information in unprecedented ways.This transformation has extended to online recruitment, where job postings on corporate websites and career portals attract a global pool of qualified candidates.However, this convenience has also opened doors to scammers, posing threats to applicants' privacy and tarnishing companies' reputations.This case study delves into the detection of recruitment fraud and scams, employing three distinct machine learning models to construct an effective detection system.By incorporating various organizational, job description, and remuneration features, the proposed system utilizes Support Vector Machine, Random Forest, and Naive Bayes Classifier algorithms to differentiate between genuine and false job postings.Feature extraction techniques such as Term Frequency-Inverse Document Frequency (TF-IDF) and Bag-of-Words (BoW) are employed to derive meaningful insights from the data.An ensemble model is then formed by training these three models on different subsets of the data and aggregating their predictions through a simple majority vote.This approach yields promising results, with an accuracy exceeding 98.18% achieved using the Random Forest Model.