Try it here


Mental health is becoming an increasing problem in the world, especially for students in school. Poor mental health, untreated, can lead to a whole host of terrible consequences including self-harm, depression, suicide, and more. That's why we've created MentalSafeSpace.

What it does

MentalSafeSpace uses state-of-the art machine learning technology to detect mental health flags in text messages early on so those who need help can receive the support they need, when they need it. MentalSafeSpace does this in a beautiful, easy-to-use, room-based chatting system that connects anyone, worldwide over the internet.

How we built it

We built this app with a few different technologies. Firstly, HTML, CSS + Bootstrap, and JS for the front-end chat interface. Next, we used Node.js, express,, and MongoDB for the back-end. Finally, the star of the show, we used a machine learning model, trained on the Google Cloud Platform to perform sentiment and risk analysis on text messages.

Accomplishments that we're proud of

We built a fully functioning app in less than 24 hours that we believe is a starting point for a useful solution that will help people and potentially save lives. We also learned many new technologies and how to intertwine them together as a team.

Challenges and what we learned

We decided to challenge ourselves for this week's hackathon. Our goal was to learn and use technologies that we've never used before. Our front-end developer, Samer, used Javascript for the first time to create this application. Our back-end developer, Matthews, learned Express,, and MongoDB in the process of creating MentalSafeSpace. Our machine learning expert, Rohan, used GCP for the first time to train the model.

What's next for MentalSafeSpace

We want to improve this platform and make it a real product that schools and organizations can use to help students and other people.

Share this project: