COMPARATIVE STUDY OF FAKE NEWS DETECTION BETWEEN MACHINE LEARNING AND DEEP LEARNING APPROACHES
International Research Journal of Modernization in Engineering Technology and Science · 2023
Most of the people now-a-days prefer to read the news via social media over internet.Many websites are publishing the news and provide the source of authentication.The question is how to authenticate the news and articles which are circulated among social media like WhatsApp groups, Facebook Pages, Twitter, and other micro blogs & social networking sites.It is harmful for the society to believe on the rumors and pretend to be a news.The need of an hour is to stop the rumors and focus on the correct, authenticated news articles.Aim of this project is to develop two models for detecting fake news by using Machine Learning algorithms (usingSVM) and Deep Learning algorithms (using LST) respectively.With the help of Machine learning and Deep Learning, it is tried to aggregate the news and later determine whether the news is real or fake using Support Vector Machine and Long Short-Term model.For the model, the dataset is cleaned and the data is pre-processed.Then on the pre-processed data, feature extraction techniques are used and the model is trained using both the algorithms separately to get two different models using SVM algorithm and LSTM algorithm respectively.Confusion Matrix, Classification reports and accuracies of both the models are calculated and compared to find the best model for Fake News Detection.SVM Classifier gave 99.29% accuracy and LSTM classifier gave 99.54% accuracy.Both the algorithms gave good accuracies but LSTM gave better results compared to SVM in classifying the news articles.The major contribution of this project is to find the better fit algorithm and techniques for Fake News Detection between SVM and LSTM algorithms by comparing their accuracies.