A novel approach to fake news detection in social networks using genetic algorithm applying machine learning classifiers

• Published in: Multimedia tools and applications Vol. 82; no. 6; pp. 9029 - 9045
• Main Authors: Choudhury, Deepjyoti, Acharjee, Tapodhir
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2023; Springer Nature B.V
• Subjects: 1209: Recent Advances on Social Media Analytics and Multimedia Systems: Issues and Challenges; Accuracy; Classifiers; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Evolutionary algorithms; Genetic algorithms; Machine learning; Multimedia Information Systems; News media; Regression analysis; Social networks; Special Purpose and Application-Based Systems; Support vector machines; Genetic algorithm; Fake news; Social media; Machine learning
• DOI: 10.1007/s11042-022-12788-1
• ISSN: 1380-7501

Now-a-days fake news have become part and parcel of our everyday life due to its quick spreading in different social media. Fake news identification has been emerging as an important research subject due to the widespread dissemination of fake news on social and news media. Current fake news identification techniques primarily rely on the analysis of natural languages and machine learning models to assess the validity of news information in order to detect whether it is real or fake. Many traditional approaches including machine learning applications have been observed yet to detect fake news but the evolutionary based algorithms have gained lot of popularity because of their ability to converge to near optima and have low computational complexity. This motivated us to adopt a new approach with genetic algorithm to solve the fake news detection problem. In this paper, a comparative analysis is presented among SVM, Naïve Bayes, Random Forest and Logistic Regression classifiers to detect fake news applying on different datasets. SVM classifier has achieved the highest accuracy with 61%, 97% and 96% in Liar, Fake Job Posting and Fake News datasets respectively. Again, SVM, Naïve Bayes, Random Forest and Logistic Regression are considered as the fitness function in our novel GA based fake news detection algorithm. In our proposed algorithm, SVM and LR classifiers both achieved 61% accuracy in LIAR dataset and SVM and RF attained the highest accuracy as 97% in the fake job posting dataset.