A Proposal and Evaluation of Learning Advising using a Generative AI

Abstract

In this paper, we propose and evaluate a method in which learner’s learning history and information about goal setting and reflection are provided as prompts to Large Language Models (LLM) that enables automated learning advice generated. The proposed approach allows us to generate advice messages that are relevant to the learner’s learning properties, using learners’ own sentences for reflections and goal settings. The generated advice is evaluated from the point of view whether it is similar to the actual teacher’s one.