Have you ever felt overwhelmed by school, friends, and life in college? From tough classes to social events and worries about the future, it's a lot to handle!
The project goal was clear: identify stress and mental health issues among university students to raise awareness and provide essential support. Here's how we tackled it:
-
Data Collection: We gathered datasets from various platforms and integrated real-time responses from university students to enrich our dataset.
-
Exploratory Data Analysis (EDA): Deep dive into patterns provided invaluable insights into student behaviors and mental health indicators.
-
Data Preprocessing: Ensured data integrity by meticulously cleaning and preprocessing the dataset, eliminating errors and missing data.
-
Clustering and Classification: Employed clustering techniques to categorize students based on their mental health scores and issues. Leveraged classification models to predict new students' mental health categories.
-
Technological Tools: Utilized Python and libraries like Pandas, NumPy, and Scikit-learn. Kaggle and real-time survey platforms facilitated data collection.
-
Model Deployment: Our user-friendly form allows students to input their mental health scores, providing personalized support suggestions based on their category.
This project demonstrates the power of machine learning in addressing real-world challenges and promoting mental health awareness. Moving forward, we're committed to refining our model and expanding its reach to benefit more students across universities.
This notebook is created by Connect X AI team.
AI team director Ammar Thabet