Abstract:
Fake News is misinformation that misleads society by presenting it as authentic news or we say fabricated news which misleads us. One of the biggest problems among govern...View moreMetadata
Abstract:
Fake News is misinformation that misleads society by presenting it as authentic news or we say fabricated news which misleads us. One of the biggest problems among governments is fake news. In this paper, we aim to tackle this problem using the computational model that uses machine learning digital model algorithms for accurate misleading information detection. We used Count Vectorizer as the feature extraction technique and many different machine learning classifiers such as Naïve Bayes, The Decision tree, Random Decision Forest, etc. We also used the records to train and test the model which we split in a ratio of 4:1. The results of our model used a count vectorizer as feature extraction and a different classifier as Naïve Bayes with an accuracy of 93.10 a DT(decision tree) with 96.49% accuracy, an SVM(support vector machine) with 97.49% accuracy, and an RDF(random decision forest) with 98.49% accuracy. The research concludes that the RDF (Random Decision Forest classifier0 is suitable for better accuracy.
Date of Conference: 14-16 December 2022
Date Added to IEEE Xplore: 22 March 2023
ISBN Information: