Prediction the Electronic Gadget Addiction of Students using Machine Learning

ABSTRACT

The rapid proliferation of electronic gadgets has raised concerns about addiction among students, impacting their academic performance and overall well-being. This project focuses on predicting electronic gadget addiction in students using a machine learning approach, specifically employing Random Forest (RF) algorithms.
By analyzing a variety of factors, including usage patterns, academic performance, social interactions, and psychological profiles, the model aims to identify students at risk of addiction.
The dataset comprises responses from surveys and behavioral assessments, enabling the RF algorithm to capture complex interactions between variables and provide accurate predictions.
This predictive model not only aids in early identification of addiction but also informs educational institutions and parents about the necessity of implementing effective interventions.
The system is designed to be user-friendly, offering insights and recommendations based on the predictive analysis, ultimately promoting healthier gadget usage habits among students. Through this project, we aim to contribute to the understanding of electronic gadget addiction and its implications, fostering a balanced approach to technology in education.

EXISTING SYSTEM

Manual Surveys and Questionnaires

Traditional methods involve surveys and questionnaires where students self-report their gadget usage, academic performance, and well-being. These surveys are often conducted by schools, researchers, or mental health professionals.

Basic Statistical Analysis

Some systems use basic statistical methods to analyze data collected from students, such as correlating screen time with academic performance or mental health indicators. These methods might involve simple correlation or regression analysis.

Behavioral Monitoring Software

Certain schools and parents use software to monitor students’ gadget usage, including time spent on specific apps or websites. This data is then reviewed to assess potential overuse.

DISADVANTAGES

Self-reported data can be inaccurate due to biases or students’ reluctance to disclose their actual usage patterns. The analysis is often manual and may not capture complex relationships between variables.
While these tools provide real-time monitoring, they do not offer predictive insights. The data collected is often used reactively, rather than proactively, and there is a risk of invading students’ privacy.
Basic statistical analysis often fails to capture the non-linear relationships between variables. It also lacks predictive capabilities, meaning it can identify existing issues but cannot forecast future outcomes.
Existing models may lack accuracy due to limited data and simplistic algorithms. They might not be widely implemented or accessible to most schools and parents, limiting their practical application.

PROPOSED SYSTEM

The proposed system aims to predict the impact of electronic gadget addiction on students’ lives by utilizing the Random Forest algorithm, a powerful and versatile machine learning technique.
The system will focus on analyzing various factors such as screen time, academic performance, sleep patterns, and social behavior to predict the likelihood of negative outcomes associated with excessive gadget use.
The proposed system aims to predict the impact of electronic gadget addiction on students’ lives using the Random Forest algorithm, a powerful machine learning technique known for its robustness and accuracy.
This system will collect and analyze data from various sources, including screen time, academic performance, sleep patterns, and social behavior, to identify and forecast potential negative outcomes associated with excessive gadget use.
By leveraging Random Forest, the system can handle complex interactions between multiple factors, providing reliable predictions while highlighting the most influential variables.
Additionally, the system will offer personalized recommendations and alerts based on the predicted risks, enabling timely intervention to mitigate the adverse effects of gadget addiction.

PROJECT DEMO VIDEO

HARDWARE REQUIREMENTS:

SOFTWARE REQUIREMENTS:

Including Packages

=======================

Specialization =======================

2 Comments