Purpose: The purpose of this research is to address the issue of fake news circulating on social media platforms, with a particular focus on Twitter. The aim is to develop a model that automates the detection of fabricated news messages in Twitter datasets by predicting accuracy ratings. The goal is to contribute to maintaining a robust online media and social networking environment. Methodology: To achieve the purpose, the researchers employ a methodology that involves learning how to anticipate precision evaluations of news messages. The dataset used for the analysis consists of tweets. Five popular machine learning techniques, namely Support Vector Machine (SVM), Naive Bayes Method, Logistic Regression, and Recurrent Neural Network models, are individually compared to assess their effectiveness in classifying fake news. The researchers utilize these techniques to train the model and evaluate its performance. Findings: The research findings indicate that both Support Vector Machine (SVM) and Naive Bayes classifier outperform the other machine learning techniques in detecting fake news on Twitter. The model developed using these techniques demonstrates superior classification performance on the dataset of tweets, suggesting their effectiveness in automated fake news detection. The findings validate the potential of machine learning algorithms in addressing the problem of fake news on social media platforms, specifically Twitter. Recommendations: Based on the findings, the researchers recommend the implementation of the Support Vector Machine (SVM) and Naive Bayes classifier algorithms for automated fake news detection on Twitter. These techniques have proven to be effective in identifying fabricated news messages. It is crucial for social media platforms to integrate such models into their systems to enhance the accuracy of news distribution and protect users from misinformation. Additionally, ongoing research and development efforts should continue to improve and refine these algorithms, considering the evolving nature of fake news and the need for robust detection methods.

Naive Based Classifier, News, Prediction, Recommendation, Support Vector Machine (SVM), Fake News, Twitter, Social Media, Data quality, Counterfeit, Machine Learning, Deep learning