Unveiling the Truth: Detecting Fake News Using SVM and TF-IDF

The spread of fake news on social media platforms such as Facebook, Instagram, and X has become a significant issue in the digital era due to its negative societal and informational impacts. The rapid dissemination of unverified information often leads to misinformation and confusion, highlighting the critical need for reliable detection methods. This study aims to classify and detect fake news by optimizing the Support Vector Machine (SVM) machine learning algorithm using the Term Frequency-Inverse Document Frequency (TFIDF) technique. Two publicly available Kaggle datasets, containing labeled fake and real news, were utilized as the foundation for this research. The research results demonstrate that the SVM algorithm, when optimized with TF-IDF, achieved the highest accuracy of 99.6% compared to other commonly used machine learning algorithms such as Random Forest and Logistic Regression. This highlights the effectiveness of TF-IDF in improving the feature extraction process, enabling the model to better differentiate between fake and real news. These findings underscore the potential of SVM as a reliable tool for combating misinformation. To further enhance fake news detection, future research should explore the use of more comprehensive, multilingual, and complex datasets to better reflect real-world scenarios. Additionally, employing transformer-based approaches, such as BERT, GPT, or similar models, could provide a deeper understanding of linguistic context and semantic relationships, ultimately improving the robustness and accuracy of fake news detection systems.