ADAPTIVE LEARNING PLATFORMS FOR PERFORMING ARTS

Abstract [English]

The performing arts education practices are changing with the emergence of abstract learning platforms, which allow individualized, data-driven, and responsive learning environments, which resonate with individual learners and their artistic skills and developmental paths. Conventional performing arts pedagogy has been based on the studio-based teaching approach and the master/apprentice paradigm that has had difficulties in scaling, objectively measuring skill development as well as dynamically addressing the needs of various learners. In this study, the researcher suggests an adaptive learning model in performing arts to combine learning theories with multimodal data acquisition and artificial intelligence in improving the skill learning process in the learning of music, dance and theatre. The platform is based on the constructivist and experiential learning paradigms, and it implies the cognitive, emotional, and embodied aspects of artistic learning, focusing on practice, feedback, and reflective iteration. The suggested framework will include profiling of learners, modeling skills, and curriculum sequencing engines, which dynamically adjust the instructional material. Multimodal cues such as motion capture, pose detection, audio rhythm detection and visual gesture recognition are used to capture the subtle elements of performance such as timing, expressiveness, posture, and coordination. Machine learning (including supervised and unsupervised skill evaluation methods and reinforcement learning methods to schedule adaptive practice) allow the personalization of the process and provided feedback to be constantly adjusted and performance-sensitive. Deep learning models also contribute to the discussion of complex movement patterns, sound features and expressive gestures in the arts.