FAKE NEWS DETECTION USING NATURAL LANGUAGE PROCESSING

In the digital age, false news is rapidly spreading, posing a severe danger to the integrity of information flow and the dependability of news sources. Thus, keeping an educated society has become dependent on the identification of bogus news. Natural language processing (NLP) techniques have become useful tools for spotting and preventing fake news in recent years. This abstract gives a thorough explanation of how NLP is used in false news identification. Numerous NLP strategies have been used in false news detection, starting with feature extraction and text preparation techniques that make it possible to effectively represent textual data. This study has been able to develop a model that can be used in detecting fake news with the use of Natural Language Processing (NLP). The proposed model was implemented with the use of support vector machine (SVM) with and without standard scaler in a python environment with use of Jupiter platform and the outcome result was evaluated using the performance matrices calculator such as Sensitivity, specificity, precision, Accuracy and F1-Score. The result generated shows that the accuracy of the model dataset is while using SVM with standard scaler was 95.00%, the precision result was 56.45% whereas F-measure showed 94.97% respectively. In summary, this model has given a thorough explanation of how NLP approaches are used in fake news identification. It is a useful tool for scholars and professionals who want to learn how NLP can be used to stop the extension of wrong information, maintain the credibility of information, and promote an informed society.