An Ensemble Machine Learning Approach for Fake News Detection and Classification Using a Soft Voting Classifier

Abstract

Fake news has grown in popularity and spread as a result of increased insecurity, political events, and pandemics, among other things. This study used an ensemble machine learning technique to better predict fake news on social media based on the content of news articles. The proposed model used a soft voting classifier to aggregate four machine learning algorithms, namely, Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression, for the classification of news articles as fake or real. GridSearchCV was used to fine-tune the algorithms to get the optimal results during the training process. A Kaggle dataset was used for the experiment; it was comprised of both false and true news. Performance evaluation metrics were used to measure the performance of the base learners and our proposed ensemble technique on the dataset. The results of our experiment show that the proposed ensemble approach produced the highest accuracy, precision, recall, and F1_score values of 93%, 94%, 92%, and 93%, respectively, on the dataset as compared to the individual learners. This approach may also be used in other classification techniques for spam detection, sentiment analysis, and prediction of loan eligibility, among other things.

Offensive Language Detection Using Soft Voting Ensemble Model

“…Besides classifying offensive content, soft voting classifiers were also used to detect fake news. The study [9] compared Naïve Bayes, SVM, Logistic Regression, Random Forest, hard voting, and soft voting to predict fake news on social media. The soft voting method surpassed the other classifiers with 93% in the F1 score.…”