Logo des Repositoriums

Auflistung nach Autor:in "Dieing, Thilo I."

1 - 2 von 2
  • Konferenzbeitrag
    Developing a Personalized Study Program Recommender
    (Proceedings of DELFI Workshops 2024, 2024) Scheffler, Marc; Dieing, Thilo I.; Cohausz, Lea
    This paper presents a recommender system designed to match prospective students with study programs in Baden-Württemberg, Germany, streamlining the selection process by providing personalized recommendations based on user queries. Utilizing data from approximately 1,500 study programs and employing natural language processing and machine learning techniques, specifically the German fastText model for word embeddings, our system captures the semantic relationships between user queries and program descriptions. We evaluated the system’s performance using both manual test cases and automated validation methods. The manual evaluation involved subjective assessments by multiple raters, while the automated approach utilized self-supervised keyword-based approaches. The results demonstrate the system’s effectiveness in enhancing the study program selection process.
  • Konferenzbeitrag
    Enhancing Chatbot-Assisted Study Program Orientation
    (Proceedings of DELFI Workshops 2024, 2024) Dieing, Thilo I.; Scheffler, Marc; Cohausz, Lea
    As university dropout rates increase, implementing innovative solutions is crucial to reduce attrition. Aligning students’ interests with their study programs enhances academic success, satisfaction, and retention. This paper presents a novel approach using open-source Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) to develop a semi-open-domain knowledge chatbot. The chatbot generates informed responses and recommendations to diverse student queries by retrieving relevant data while maintaining ethical standards and avoiding biased responses. When testing five model combinations on 70 prompts partially from real study advisors, results demonstrate that the RAG approach with the Mixtral LLM and RoBERTa embedding model offers superior performance. Our method for handling critical user prompts further indicates a significantly improved response quality. These findings advance service-oriented chatbots in education, aiming to reduce student attrition through accurate and helpful program recommendations.