Global Journal of Computer Science and Technology, C: Software & Data Engineering, Volume 22 Issue 2

Fake News Detection: Covid-19 Perspective Global Journal of Computer Science and Technology Volume XXII Issue II Version I 6 Year 2022 ( ) C © 2022 Global Journals Fig. 6: Data collection process • Term Frequency(TF): Term frequency calculates the frequency of a term or word occurs in a data set. • Inverse document frequency(IDF): Inverse document frequency calculates how important a word or term is in a document. In TF all words or terms are equally considered important. Thus, IDF weight down repeated words or terms and scale up the uncommon ones. f) Confusion Matrix A confusion matrix is a method of describing the classification algorithms performances [9]. A confusion matrix is a table that shows how well a classification model (or ”classifier”) performs on a testing data set for which the real values are known. The confusion matrix itself is uncomplicated, but the related terms might be complex. Fig. 9: Confusion Matrix • True Positive(TP): When the positive type is predicted exactly by a model. • True Negative(TN): When the negative type is predicted exactly by a model. • False Positive(FP): When the positive type is predicted incorrectly by a model. • False Negative(FN): When the negative type is predicted incorrectly by a model. • Accuracy: Accuracy is the ratio of accurate forecasts to overall forecasts made. • Precision: Precision is the ratio of positive results Data True News Al Jazeera BBC Times of India Fake News Politifact Health Feedback Fact Check.org TF(t) = Number of times term t appears in a document Total number of terms in the document IDF(t) = log e Total number of documents Number of documents with term t in it Accuracy = TP + TN TP + TN + FP + FN