Assessing Social Media's Impact on Mental Health: A Gaussian Naive Bayes Approach

In recent times, social media has gained immense popularity. However, there is a growing concern among individuals regarding its impact on mental well-being. Extensive research has been conducted to unravel the intricate connection between the use of social media and mental health. This study thoroughly examines the existing literature by incorporating various studies that cover topics such as machine learning for analysing depression-related sentiments and the effects of social media on specific demographic groups. The aim is to develop a comprehensive understanding of the relationships between these factors. In order to gain a deeper understanding of mental health indicators, a dataset consisting of 481 records was analysed using various techniques including pre-processing, correlation analysis, data visualisation, and Gaussian Naive Bayes predictive modelling. Based on our findings, it appears that individuals who engage with social media may experience negative impacts on their mental well-being. During our investigation, we conducted tests on different machine learning models and discovered that Gaussian Naive Bayes yielded the highest level of accuracy. The presence of multicollinearity among independent variables emphasises the importance of being cautious when interpreting research findings. This study makes a valuable contribution to our understanding of the complexities involved in using social media platforms while managing mental health issues. By focusing on the intersection of technology and psychiatric illnesses, it lays the groundwork for future research and interventions in this important area.