Mooody

Homepage of Moody
Conversation with Mr. Moo

Inspiration

Both we and our peers have struggled with mental health. Therapy is not the most affordable or accessible option for students, so we wanted to create a web app that offers journaling and interactive mental health support using Gemini and HuggingFace Models to offer the best experience to our users.

What it does

Mooody is an interactive mental health journaling web app used to track mood changes with the help of AI tools. Users can track their emotions through journal entries and drawings, as well as engage in conversations with an AI-powered chatbot that serves as a therapist.

How we built it

For our web app, we built the frontend using Streamlit. For the journal entry features, we used the pandas library, matplotlib for plotting moods over time, Gemini API for the AI therapist chatbot, the HuggingFace machine learning model for detecting emotion in journal entries, and built-in Streamlit functions for the sketchbook. We also used CSS + HTML to design the custom cow cursor!

Challenges we ran into

We ran into difficulties using Streamlit as well as accurately storing data + accurately representing data using CSV files. We also ran into difficulties with response accuracy with the AI therapist chatbot.

Accomplishments that we're proud of

We are proud of creating a web app that can inspire change in the community in a short period of time. We are also proud of the fact that we have used relevant technologies up to today's standards.

What we learned

When creating Mooody, we learned an alternative pathway to creating seamless frontend designs using Streamlit instead of using HTML and CSS. We also learned to effectively implement and the Gemini API into a web app.

What's next for Mooody

We want to implement an emotion classification tool using OpenCV + TensorFlow, and also include interactive games based on the user's current emotional state (can be done by using Unity or even Pygame.