This project aims to detect individuals' levels of social media addiction by leveraging machine learning algorithms to analyze various behavioral patterns and interactions with social media platforms. By collecting and processing data related to users' social media usage, the system can assess the severity of addiction and provide insights for intervention or support. The project aims to raise awareness about the impact of excessive social media use on mental health and well-being.
The detection process involves analyzing factors such as the frequency and duration of social media usage, types of activities conducted on social media platforms, levels of interaction, and signs of addiction or compulsive behavior. Through this analysis, the system can classify individuals into varying levels of addiction, ranging from mild to severe.
Key features of this project include accessing data from social media-ready datasets, training machine learning models for addiction level classification, and developing a user-friendly interface for accessing and interpreting results.
To predict social media addiction level using this project, you can follow the steps below:
Load or train the model using a sample dataset. Prepare input data. Make predictions using the model. Analyze the predicted addiction level and evaluate the results. existing Git repository with the following command:
git clone https://github.com/alp55/Social-Media-Addiction-Level-Detection.git
&
Email: alperenulutas1@gmail.com , email: sanemsakarya45@gmail.com
[1] Zara, M. C., & Monteiro, L. H. (2021). The negative impact of technological advancements on mental health: An epidemiological approach. Applied Mathematics and Computation, 396, 125905.