INTELLIGENT RECOMMENDATION SYSTEMS FOR ART COURSES

Abstract

This paper will describe a detailed outline of an emotion-based intelligent recommendation system to suit the field of art education. The model proposed unites cognitive modeling, hybrid algorithms of AI, and affective computing to customize the art course recommendation, which fits the creative style and emotional interest of the learners. The system also allows adaptive, context-based learning through the integration of content based, collaborative and reinforcement learning methods with pedagogical reasoning. Experimental measurements prove that the hybrid model is more accurate (Precision@10 = 0.89, NDCG = 0.86) and high affective congruence (Affective Match Ratio = 0.83) compared to the classical approaches to recommendation. Qualitative measures also prove the increased attentiveness of learners, diversity of creativity, and emotional connection. The framework provides a platform of ethical, transparent, and compassionate AI in art pedagogy-developing human-AI cooperation to establish creativity, inclusivity, and contemplative art development.