A Research on Fake News Detection Using Machine Learning Algorithm

Fake news may have different meaning to different individuals. For the purpose of this paper, we will go by the definition of fake news as those reports that are bogus: The story itself is created, with no relation to realities, sources or statements. In this research on fake news detection through machine learning algorithms, we are implementing two feature selection approaches toward the problem: Bag of words model and TF-IDF vectorization model and are using four classifiers namely, logistic regression classifier, naive Bayes classifier, random forest classifier and passive aggressive classifier for classification purpose. This research is being conducted on two separate datasets, among which for bag of words model along with logistic regression classifier yields average F1 Score of 92.16% and for TF-IDF vectorization, logistic regression classifier yields average F1 Score of 93.47%. Also, passive aggressive classifier works well with high volume of data along with TF-IDF as can be seen by highest increase in F1 Score.