CS66-RE10 :: Personalized Music Therapy for Dementia Care

Personalized Music Therapy for Dementia Care

details
Personalized Music Therapy for Dementia Care is a research project that compares three music recommendation pipelines for subjects with dementia: a traditional hybrid recommender, a Vector Retrieval-Augmented Generation (RAG) pipeline, and a Knowledge Graph RAG (KG-RAG) pipeline. All three use the same 7,003 Billboard Hot 100 Year-End songs, the same MMSE-based safety rules, and the same LLM judge, and are evaluated on 260 synthetic personas. On the main set (n = 200), KG-RAG kept the most highly relevant songs and ranked them best (p < 0.001) in both cold and warm sessions.
tools & techniques
Programming language: Python Knowledge graph: NetworkX LLMs: GPT-5.6 Luna (reranking), Claude Sonnet 5.5 (synthetic personas), Gemini 3.8 Flash (LLM-as-judge) Techniques: Retrieval-Augmented Generation, Knowledge Graph RAG, collaborative filtering, synthetic persona generation, LLM-as-judge Version control: GitHub Code editor: VS Code
author
MS.Ngwe yee pearl Ou
รหัสนักศึกษา 66130500818
66130500818@ad.sit.kmutt.ac.th
advisor
Jonathan Hoyin Chan
Chakarida Nukoolkit