Paper Title
News Entity Classification using NLP

Abstract
Abstract – The paper produces identification of forging news is proposed in this research utilizing Machine Learning approaches with several algorithms to optimize accuracy. This paper proposes a mechanism for determining if news is false or not. We'll train a model to classify false news using the NLP approach TF-IDF vectorization, which shows us how each phrase is used in the news or dataset. This algorithm examines false news detection and digs out prior machine learning models to see which is the best. Using text analysis tools such as the Scikit-learn package and Natural Language Processing (NLP), To tokenize the collected data set, we utilize the Scikit-learn module. To enhance the efficiency of the model, we employ multiple machine learning techniques such as naive bayes, SVM, and Max Entropy to train and evaluate the data sets. We will also be working with machine learning algorithms like as pos-tagging and TF-IDF to acquire the greatest possible accuracy. Keywords – NLP, Machine learning, Naive Bayes, SVM, Max Entropy, POS-Tagging and TF-IDF.