A Machine Learning Approach to Predict Social Media Addiction of Bangladeshi People during COVID-19

Abstract

The world is in an extremely precarious situation, with coronavirus posing a serious threat. To be safe, staying at home is the best option right now. People nowadays spend the significant amount of their time on social media platforms. Just as social media has stood by people during this pandemic, it has also caused trouble in some cases. Excessive use of social media has an adverse effect on mental and physical wellbeing. Besides, the over usage of social media leads to negative impact on once social life, moreover it can also lead people to make various dangerous crimes. In this research study, the use of social media by Bangladeshi people throughout the year 2021 was examined in order to anticipate their level of addiction to this COVID-19 circumstance. The data was gathered from people of various occupations, and the levels of addiction has been analyzed with the help of professionals and several internet sites. Using some methods and machine learning classifiers, their addiction to social media has been predicted in which the levels are categorized into four class labels. Several data mining techniques, methods and machine learning classifiers have been applied and found the maximum accuracy, 94.05% in logistic regression.