Social Media and Mental Health Overview

This project investigates the relationship between social media usage and mental health, using data-driven techniques and machine learning models to predict mental health outcomes based on social media interaction patterns. The study aims to explore how factors such as screen time, platform usage, and content engagement correlate with mental health issues such as anxiety, depression, and self-esteem.

Key Features

Data Collection: Social media usage data and mental health questionnaires, using Likert scales to quantify symptoms of anxiety, depression, and self-esteem. Exploratory Data Analysis (EDA): Insights into how specific social media behaviors correlate with mental health outcomes. Predictive Modeling: Building machine learning models to predict mental health outcomes based on usage patterns. Model Evaluation: Evaluating the performance of predictive models using accuracy, precision, recall, and F1-score. Data

The dataset includes anonymized social media activity logs and responses to mental health surveys, capturing aspects such as:

Social Media Metrics: Time spent, frequency of usage, platform preferences. Mental Health Assessments: Likert scale questions on anxiety, self-esteem, and depression. Data Preprocessing Cleaning and filtering the data for analysis. Normalizing the data to remove outliers and inconsistencies. Algorithms and Models

Logistic Regression Random Forest Support Vector Machine (SVM) K-Nearest Neighbors (KNN) These models are used to predict mental health outcomes based on the features derived from the social media data.

---