Scopus Indexed Publications

Paper Details

Detection of Facebook Addiction Using Machine Learning
Md. Zahirul Islam, Md. Sadekur Rahman, Md. Tarek Habib, Ziniatul Jannat,

A popular social media platform today is Facebook. Facebook addiction is ill-defined. As responsible citizens, we must help society avoid this addiction. Using machine learning techniques, we can forecast the danger of being hooked to Facebook. First, we look into the elements that affect Facebook. This article is great since it informs readers about the hazards of addiction and the elements that lead to it. More than 1,000 people of different ages and backgrounds, addicted or not, have provided data. This article examines people's Facebook addiction and everyday routine. We use SVM, k-nearest neighbors, decision trees, Gaussian naive Bayes, logistic regression, and random forest to predict Facebook addiction. SVM is the most commonly used algorithm, followed by k-nearest neighbors and decision tree. We evaluate their overall performance using a variety of metrics. We utilize PCA to mathematically reduce data. Our results show that SVM outperforms the other algorithms by 85.00%.

Facebook addiction Prediction system Machine learning classifier SVM PCA Decision tree
Journal or Conference Name
Lecture Notes in Networks and Systems
Publication Year