PrepPal is a chatbot developed to assist users by providing instant responses to their queries. The system was built using Python with Natural Language Processing (NLP) and Machine Learning techniques to understand and classify user intents. The chatbot uses a Bag-of-Words model, tokenization, and stemming during text preprocessing to convert user input into a structured format. A Multi-Layer Perceptron (MLP) neural network, implemented using the PyTorch framework, was trained on labeled intent data to classify queries accurately. The application backend was developed using Python and Flask, while the frontend interface was designed using HTML, CSS, and JavaScript. The chatbot processes user input, predicts the most relevant intent using a trained model, and generates appropriate responses from a predefined knowledge base. PrepPal aims to provide 24/7 student assistance, improving accessibility to information and enhancing the overall learning experience. The project demonstrates practical implementation of NLP, supervised learning, neural networks, and chatbot development.
- An AI-based student support chatbot for instant query resolution
- Applied Natural Language Processing (NLP) and Machine Learning for intent understanding
- Implemented preprocessing techniques: tokenization, stemming, Bag-of-Words
- Built and trained an MLP (Multi-Layer Perceptron) neural network using PyTorch
- Frontend: HTML, CSS, JavaScript
- Backend: Python and Flask
- Enabled intent prediction and response generation from a structured knowledge base
- Provides 24/7 automated assistance, improving accessibility and user experience