Trends and topics in arts education and artificial intelligence: a systematic review using a human-in-the-loop model

This project describes a step‑by‑step method for doing a systematic literature review that looks at both arts education and artificial intelligence, using a human‑in‑the‑loop (HITL) approach. Because AI tools are shaping how we teach creativity, we need strong, partly automated systems to map the changing research field. The system combines natural language processing (NLP) with interactive machine learning to sort research papers, reducing the amount of manual work needed in a traditional systematic review. Human feedback is fed back into the active‑learning loop, letting the model sharpen its categories for complex, cross‑disciplinary topics. It uses advanced topic‑modeling methods like Latent Dirichlet Allocation (LDA) or BERT‑based embeddings, together with an interactive

annotation tool where experts check and fix the algorithm’s labels. This mix of human and machine gives high accuracy when spotting major trends, changes in teaching methods, and new technology uses in arts education. In the end, the project offers a full evaluation framework that measures how efficient, accurate, and scalable HITL models are versus fully manual or fully automated reviews. The results give useful guidance for researchers working across AI and other fields.

Message: Hi FE, I need help with “Trends and topics in arts education and artificial intelligence: a systematic review using a human-in-the-loop model” in “Computer Science & Engineering”