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.
In today's digital age, social media usage has become ubiquitous, especially among students. While social media offers various benefits, excessive use can lead to distractions and affect academic performance. This project utilizes machine learning techniques to predict concentration difficulties based on social media usage and demographic information.
The dataset used in this project was sourced from Kaggle, a popular platform for data science and machine learning datasets. The dataset contains the following types of information.
- Age: The age of the participant.
- Sex: The gender of the participant (e.g., Male, Female, Other).
- Relationship: Current relationship status (e.g., Single, In a Relationship, Married).
- Occupation: Current occupation status (e.g., Student, Employed, Unemployed).
- Affiliations: Type of organizations the participant is affiliated with (e.g., educational institutions, workplaces).
- Social Media User?: Whether the participant uses social media (Yes/No).
- Platforms Used: Common social media platforms used by the participant.
- Time Spent: Average time spent on social media every day.
- Q1: How often the participant uses social media without a specific purpose.
- Q2: How often the participant gets distracted by social media when busy.
- Q3: Whether the participant feels restless if they haven't used social media in a while.
- Q4: How often the participant seeks validation from features of social media.
- Q5: On a scale of 1 to 5, how much the participant is bothered by worries.
- Q6: How often the participant feels depressed or down.
- Q7: On a scale of 1-5, how often the participant compares themselves to other successful people through social media.
- Q8: General feelings about these comparisons.
- Target 1: On a scale of 1 to 5, how easily the participant is distracted.
- Target 2: Whether the participant finds it difficult to concentrate on things.
- Target 3: On a scale of 1 to 5, how frequently the participant's interest in daily activities fluctuates.
- Data Collection: The data was sourced from Kaggle and consists of survey responses.
- Data Preprocessing: Cleaning and preparing the data for analysis.
- Feature Engineering: Creating and selecting relevant features for the model.
- Model Training: Training various machine learning models (e.g., Logistic Regression, Decision Trees, Random Forest, SVM).
- Model Evaluation: Evaluating model performance using metrics such as accuracy, precision, recall, and F1 score.
- Model Selection: Choosing the best-performing model based on evaluation metrics.
- Deployment: Deploying the model for real-world use.
We welcome contributions to improve this project. If you have any ideas, suggestions, or bug reports, please open an issue or submit a pull request.
This project is licensed under the MIT License. See the LICENSE file for details.