DBIS

The main objective of this thesis is to develop a Moodle chatbot that utilizes the latest advancements in Natural Language Processing (NLP) techniques, particularly in the areas of Natural Language Understanding (NLU) and Natural Language Generation (NLG). The chatbot will be integrated into online courses to provide educational and organizational support to students. It will be capable of understanding and responding to various questions related to the course materials, answering inquiries about organizational matters such as lecture schedules and exam dates, and assisting students in their learning progress. Integrating state-of-the-art NLP techniques, including generative pre-trained models like ChatGPT, will enable the chatbot to generate human-like responses and provide detailed explanations to students’ queries. To ensure the accuracy and reliability of the generated answers, the thesis will also explore using fact-verification techniques to verify the truthfulness of the text outputs. The proposed chatbot will be evaluated from a technical perspective, focusing on the accuracy and performance of the NLP components, and from a user perspective, assessing its usefulness, usability, and impact on students’ learning experience.