Classifying Misinformation of User Credibility in Social Media Using Supervised Learning

The growth of the internet and technology has had a significanteffect on social interactions. False information has become an importantresearch topic due to the massive amount of misinformed content on socialnetworks. It is very easy for any user to spread misinformation through themedia. Therefore, misinformation is a problem for professionals, organizers,and societies. Hence, it is essential to observe the credibility and validity of theNews articles being shared on social media. The core challenge is to distinguish the difference between accurate and false information. Recent studiesfocus on News article content, such as News titles and descriptions, whichhas limited their achievements. However, there are two ordinarily agreed-uponfeatures of misinformation: first, the title and text of an article, and second, theuser engagement. In the case of the News context, we extracted different userengagements with articles, for example, tweets, i.e., read-only, user retweets,likes, and shares. We calculate user credibility and combine it with articlecontent with the user’s context. After combining both features, we used threeNatural language processing (NLP) feature extraction techniques, i.e., TermFrequency-Inverse Document Frequency (TF-IDF), Count-Vectorizer (CV),and Hashing-Vectorizer (HV). Then, we applied different machine learningclassifiers to classify misinformation as real or fake. Therefore, we used aSupport Vector Machine (SVM), Naive Byes (NB), Random Forest (RF),Decision Tree (DT), Gradient Boosting (GB), and K-Nearest Neighbors(KNN). The proposed method has been tested on a real-world dataset, i.e.,“fakenewsnet”. We refine the fakenewsnet dataset repository according toour required features. The dataset contains 23000+ articles with millionsof user engagements. The highest accuracy score is 93.4%. The proposedmodel achieves its highest accuracy using count vector features and a randomforest classifier. Our discoveries confirmed that the proposed classifier wouldeffectively classify misinformation in social networks.