StudySensei

Inspiration
Studying can often feel overwhelming and lonely, especially for high school students balancing many subjects and deadlines. I wanted to create something that acts like a supportive study buddy, one that not only tracks your study time but also understands how you feel and offers personalized tips to keep you motivated and focused.

What it does
StudySensei allows you to start and stop study sessions while tracking the time spent on each subject. After each session, it asks you to reflect on how it went and uses natural language processing to analyze your mood from your feedback. Based on this, it offers helpful suggestions to improve your study habits. It also includes a Pomodoro timer for focused work sessions and visualizes your study patterns over time to help you track your progress.

How I built it
I created StudySensei using Python and Streamlit, which made it easy to build an interactive web app quickly without needing complex frontend skills. To analyze feedback, I used the TextBlob library to perform sentiment analysis and understand the user's emotions. I stored session data in CSV files and used matplotlib to generate charts showing study trends. The combination of these tools let me create a responsive and user-friendly experience.

Challenges I ran into
Managing the session state within Streamlit was tricky. I had to ensure timers started and stopped correctly without confusing the user, which took some trial and error. Crafting feedback suggestions that felt helpful and natural rather than robotic was another challenge. I also had to be careful with reading and writing data to avoid losing users' study logs.

Accomplishments that I am proud of
I am proud of creating a fully functional AI-powered study coach that beginner programmers can understand and use. The app integrates session tracking, sentiment analysis, and visual progress reports in a simple interface. Getting the Pomodoro timer to work smoothly and having personalized, mood-based suggestions felt like a big achievement.

What I learned
This project deepened our understanding of combining AI techniques with user-centered design. I gained good practical experience with Streamlit's state management, natural language processing, and data visualization. Most importantly, I learned how small, thoughtful features can significantly improve study habits.

What's next for StudySensei
In the future, I plan to add user accounts so students can access their data from anywhere. I want to incorporate more advanced AI models for personalized coaching and include gamification elements to make studying more engaging. Collecting real user feedback will help me continuously improve StudySensei into a smarter, more motivating study companion.

Built With

• csv
• matplotlib
• pandas
• streamlit
• textblob