Meta-heuristic Searched-Ensemble Learning for fake news detection with optimal weighted feature selection approach

Nowadays, fake news has turned into a major problem because of the negative impact that it creates on society. Social media allows people to spread information on the internet with slight investigations and to add fewer filters than the actual content. Nowadays, the false news in the internet community is unsure, and it creates a wrong impression among the users. Detecting false news has become a critical task based on shared content. To tackle the false news growth in social media, various automatic detection schemes were evaluated. The “Natural Language Processing (NLP)” method also gives a prominent solution for false news detection. The main intention of this paper is to design and introduce an innovative false news recognition method using Meta-heuristic Searched-Ensemble Learning (MS-EL). Further, the selected features are extracted by the “Term Frequency-Inverse Document Frequency (TF-IDF)” and also Word2vec features. Here, the extracted selected features are integrated with the Hybrid Squirrel–Dragonfly Search Optimization (HS-DSO) is used to optimize the weighted feature selection approach with the fitness function of solving data variance and correlation. The proposed MS-EL is adopted in the classification part, having three sets of classifiers, Long Short-Term Memory (LSTM), Support Vector Machine (SVM), and Deep Neural Network (DNN). Here, the ensemble classifier is enhanced by the same HS-DSO that shows the parameter tuning with a high convergence rate. From the experimental outcomes, the accuracy of HS-DSO-MS-EL is 22% higher than BMO-MS-EL, 24% higher than SP-BMO-MS-EL, 30% higher than SSA-MS-EL, and 29% higher than DA-MS-EL. Thus, the experimental analysis with standard datasets establishes that the introduced fake news detection method has gained higher accuracy than the existing models.