Dataset-POEMaster: Empowering Multi-modal Education of Chinese Poetry via Human-AI Interaction

This paper investigates the use of human-AI interaction in Chinese poetry education. Our work begins with semi-structured interviews with students, teachers, and AI experts to analyze the current difficulties in poetry education and highlight the application of AI in multimodal learning. Then, we design POEMaster, an AI-assisted interactive prototyping system that guides students in learning Chinese poetry. A between-subjects user study was conducted to examine the learning outcomes of POEMaster. The results indicate that our method can significantly improve users’ knowledge acquisition, affective learning, and self-efficacy. This research shed light on the application of human-centered AI in humanities disciplines.

This data records the experimental data from the user trial portion of the experiment, including the results of the questionnaires on knowledge acquisition, affective state, and self-efficacy for both the experimental and control groups.