Fake News Detection Using Machine Learning
Jayshree Lavhare, Sakshi Tapkir, Bhakti Balekundri, Riddhi Bhise, Rutuja Maind
1Jayshree Lavhare, Information Technology, P.G. Moze college of engineering
2Sakshi Tapkir, Information Technology, P.G. Moze college of engineering
3Bhakti Balekundri, Information Technology, P.G. Moze college of engineering
4Riddhi Bhise, Information Technology, P.G. Moze college of engineering
5Rutuja Maind, Information Technology, P.G. Moze college of engineering
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The proliferation of fake news has become a significant challenge in the age of digital information, impacting public perception, trust, and decision-making. This project addresses the pressing need for real-time fake news detection using advanced machine learning techniques.
We begin by collecting a diverse dataset comprising both real and fake news articles, meticulously curated and labelled to train our machine learning models. Preprocessing techniques are applied to clean and prepare the text data, including the removal of noise and irrelevant information.
The core of our solution lies in feature extraction, where we transform textual information into numerical representations. Utilizing TF-IDF and word embeddings, we generate meaningful features that capture the essence of the content.
A range of machine learning algorithms, such as support vector machines, recurrent neural networks, and ensemble models, are employed to classify news articles into "real" or "fake" categories. Model performance is evaluated using various metrics like accuracy, precision, recall, and F1 score.
What sets this project apart is its real-time nature. We implement a system that continuously monitors news sources, processes incoming articles, and provides immediate feedback on their credibility. This system can be integrated into news platforms and social media networks to combat the spread of misinformation and disinformation in real time.
The outcomes of this research project have the potential to mitigate the harmful effects of fake news, enabling individuals to make informed decisions based on accurate information. In a world where information integrity is paramount, real-time fake news detection is an essential tool to safeguard public discourse and trust in media.
Key Words: Misinformation, Disinformation, Fake news, Sentiment Analysis, Information Verification, Cross-validation, Algorithmic Bias, Machine learning, social media mining
