Social Media Fake News Detection Using a Robust Machine Learning Model and Data-Centric Approach

Abstract

The creation and distribution of information have been transformed by the quick development of technology and the accessibility of the internet, which has increased the difficulties presented by fake news. Intentionally created to deceive, false news has become a major issue that affects social cohesion, public trust, and democratic institutions. This research investigates the development of strong frameworks for false news detection using “artificial intelligence” (AI) and “machine learning” (ML) approaches, such as ensemble models and “natural language processing” (NLP). With the goal to assure trustworthiness and scalability of the suggested solutions, the research integrates data collection, preprocessing, feature engineering, and model evaluation using an organized methodology. Kaggle data has been used to obtain experimental data. The results are verified and validated using the Python language.