FNU-BiCNN: Fake News and Fake URL Detection using Bi-CNN

Abstract

Fake news (FN) has become a big problem in today's world, recognition partly to the widespread use of social media. A wide variety of news organizations and news websites post their stories on social media. It is important to verify that the information posted is genuine and obtained from reputable sources. The intensity and sincerity of internet news cannot be quantified completely and remains a challenge. We present an FNU-BiCNN model for identifying FN and fake URLs in this study by analyzing the correctness of a report and predicting its validity. Stop words and stem words with NLTK characteristics were employed during data pre-processing. Following that, we compute the TF-IDF using LSTM, batch normalization, and dense. The WORDNET Lemmatizer is used to choose the features. Bi-LSTM with ARIMA and CNN are used to train the datasets, and various machine learning techniques are used to classify them. By deriving credibility ratings from textual data, this model develops an ensemble strategy for concurrently learning the depictions of news stories, authors, and titles. To achieve greater accuracy while using Voting ensemble classifier and compared with several machine learning algorithms such as SVM, DT, RF, KNN, and Naive Bayes were tried, and it was discovered that the voting ensemble classifier achieved the highest accuracy of 99.99%. Classifiers' accuracy, recall, and F1-Score were used to assess their performance and efficacy.