@Article{cmc.2023.034741,
AUTHOR = {Muhammad Asfand-e-Yar, Qadeer Hashir, Syed Hassan Tanvir, Wajeeha Khalil},
TITLE = {Classifying Misinformation of User Credibility in Social Media Using Supervised Learning},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {75},
YEAR = {2023},
NUMBER = {2},
PAGES = {2921--2938},
URL = {http://www.techscience.com/cmc/v75n2/51967},
ISSN = {1546-2226},
ABSTRACT = {The growth of the internet and technology has had a significant
effect on social interactions. False information has become an important
research topic due to the massive amount of misinformed content on social
networks. It is very easy for any user to spread misinformation through the
media. Therefore, misinformation is a problem for professionals, organizers,
and societies. Hence, it is essential to observe the credibility and validity of the
News articles being shared on social media. The core challenge is to distinguish the difference between accurate and false information. Recent studies
focus on News article content, such as News titles and descriptions, which
has limited their achievements. However, there are two ordinarily agreed-upon
features of misinformation: first, the title and text of an article, and second, the
user engagement. In the case of the News context, we extracted different user
engagements with articles, for example, tweets, i.e., read-only, user retweets,
likes, and shares. We calculate user credibility and combine it with article
content with the user’s context. After combining both features, we used three
Natural language processing (NLP) feature extraction techniques, i.e., Term
Frequency-Inverse Document Frequency (TF-IDF), Count-Vectorizer (CV),
and Hashing-Vectorizer (HV). Then, we applied different machine learning
classifiers to classify misinformation as real or fake. Therefore, we used a
Support 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 to
our required features. The dataset contains 23000+ articles with millions
of user engagements. The highest accuracy score is 93.4%. The proposed
model achieves its highest accuracy using count vector features and a random
forest classifier. Our discoveries confirmed that the proposed classifier would
effectively classify misinformation in social networks.},
DOI = {10.32604/cmc.2023.034741}
}