ChirpAI

Inspiration

Many teens, including some of our close friends, suffer from depression and anxiety and will vent such feelings on social media. These posts may seem unassuming but in reality can provide significant information on a persons well-being. We were extremely motivated to build an application that could help people overcome such difficulties, especially those closest to us.

What it does

ChirpAI is an intelligent virtual assistant designed to offer comprehensive mental health support. It utilizes state-of-the-art machine learning techniques to analyze user interactions and provide personalized recommendations and interventions. The key functionalities include:

Anomaly detection using K-Nearest Neighbors (KNN) algorithm Sentiment analysis using Convolutional Neural Networks (CNNs) time series analysis Statistical analysis of the emotion of each tweet

How we built it

We built ChirpAI using React Native for the frontend development, allowing us to create a cross-platform mobile application. The backend utilizes TensorFlow.js for machine learning tasks, enabling real-time analysis of user interactions. We integrated various APIs for additional functionalities, such as fetching Twitter data and accessing mental health resources.

Challenges we ran into

One of the main challenges we faced was integrating complex machine learning models into a mobile application while ensuring optimal performance. Additionally, managing state and navigation within the application posed some difficulties, especially when transitioning between different screens and handling asynchronous tasks.

Accomplishments that we're proud of

We're proud of successfully implementing advanced machine learning algorithms in a mobile application context and creating a user-friendly interface for accessing mental health support. Additionally, we're pleased with our teamwork and collaboration throughout the development process, overcoming obstacles together and delivering a polished product.

What we learned

Throughout the development of ChirpAI, we learned valuable lessons in mobile app development, machine learning integration, and user interface design. We gained a deeper understanding of the complexities involved in building a comprehensive mental health support system and the importance of empathy-driven design principles.

What's next for ChirpAI

In the future, we aim to further enhance ChirpAI by incorporating additional features such as natural language processing for more accurate sentiment analysis and expanding the range of mental health resources available through the application. We also plan to conduct user testing and gather feedback to continually improve and refine the user experience.

Built With

• chart.js
• react-native
• tensorflow
• twitter