Concentration Difficulty Prediction Model

Overview

This project aims to develop a machine learning model to predict whether individuals can concentrate on their studies based on their social media usage. The goal is to identify key factors that contribute to concentration difficulties and provide insights that could help mitigate these issues.

Dataset

The dataset used in this project was sourced from Kaggle. It contains demographic information and social media usage data of individuals, along with target variables indicating concentration difficulties.

Features and Target Variables

• Demographic Information: Age, gender, relationship status, occupation status, affiliations.
• Social Media Usage Information: Whether the participant uses social media, common platforms used, time spent on social media, frequency of use without a specific purpose, frequency of getting distracted, restlessness if not used in a while, validation seeking behavior, worries, depression, comparison behavior, and feelings about comparisons.
• Target Variables: Difficulty in concentration, distraction level, and fluctuation in interest in daily activities.

Modeling Approach

Data Preprocessing: Cleaning, handling missing values, encoding categorical variables.

Feature Engineering: Selecting relevant features, creating new features.

Model Selection: Training various machine learning models (e.g., Logistic Regression, Decision Trees, Random Forest, SVM) and selecting the best-performing one.

Model Evaluation: Evaluating model performance using metrics such as accuracy, precision, recall, and F1 score.

Deployment: Deploying the model for real-world use.

Results

The best-performing model achieved an accuracy of X% on the test set. Feature importance analysis revealed that time spent on social media and validation seeking behavior were the most influential factors affecting concentration difficulties.

Usage

1. Clone the repository:

git clone https://github.com/cepdnaclk/e19-co544-Concentration-Difficulty-Prediction-Model.git

2. Navigate to the project directory:

cd social-media-concentration-prediction

3. Run the data preprocessing script:

python preprocess.py

4. Train the model:

python train_model.py

5. Evaluate the model:

python evaluate_model.py