Published Paper Details:

In the evolving landscape of digital education, the need for personalized, scalable, and always-available student support has led to the integration of intelligent virtual assistants. This research presents the design and development of an AI-powered adaptive chatbot for e-learning platforms, utilizing deep learning and natural language processing techniques. The chatbot employs a feedforward neural network built with PyTorch, trained on categorized intents in JSON format to understand and respond to user queries. By leveraging tokenization, stemming, and bag-of-words vectorization, the system achieves effective intent classification and real-time response generation. The chatbot addresses common student inquiries, delivers educational resources, and provides navigation support, enhancing learner engagement while reducing instructor workload. The modular and lightweight architecture ensures ease of customization and scalability, making it a valuable tool for modern e-learning environments.