• Shishir Aithal
• Manjunath K N
• Sneha Hugar
• Vishalakshi V
• Venugopal B T

In the digital age, the quick spread of false news has become a serious problem that affects societal stability, public opinion, and governance. With the use of cutting-edge methods like Term Frequency-Inverse Document Frequency (TF-IDF) vectorization for feature extraction, Bidirectional Encoder Representations from Transformers (BERT) for improved contextual understanding, and Logistic Regression as the main classification model, this study suggests a thorough machine learning-based framework for identifying fake news articles. A large labelled dataset of real and fake news stories is used to train and assess the system. The system also has a real-time web interface for easy-to-use interactivity. Superior accuracy and scalability are attained by the suggested method, offering a workable remedy for the expanding disinformation issue. Additionally, to increase robustness and application, the study pinpoints areas that require improvement and future developments.

Fake news detection, machine learning, TF-IDF (Term Frequency-Inverse Document Frequency), Logistic Regression, BERT, misinformation, natural language processing, web integration

"A Machine Learning-Based Framework for Fake News Detection Using BERT, Logistic Regression, and TF-IDF Vectorization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.e817-e822, January-2025, Available :http://www.jetir.org/papers/JETIR2501600.pdf

"A Machine Learning-Based Framework for Fake News Detection Using BERT, Logistic Regression, and TF-IDF Vectorization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppe817-e822, January-2025, Available at : http://www.jetir.org/papers/JETIR2501600.pdf