Author(s)

Cheng Huang

Affiliation(s)

Shanghai Art & Design Academy, Shanghai 201899, China.

Corresponding Author

Cheng Huang

ABSTRACT

The evaluation of art design education has long faced the challenges of difficult quantification of teaching process, strong subjectivity of evaluation of creative achievements, and difficulty in taking into account the characteristics of disciplines. Based on this, this study constructs a set of AI intelligent evaluation model based on multimodal data: by integrating the three core modules of teaching process diagnosis, learning achievement evaluation and discipline characteristics adaptation, a complete evaluation system from data collection to diagnostic feedback has been established. Based on the formative evaluation theory and multiple intelligence theory, this model systematically collects the behavior data, work data and process data of teachers and students in the digital teaching environment, and then uses algorithms like decision tree analysis, LSTM time series analysis, CLIP semantic matching to realize the accurate diagnosis of the teaching process and the multi-dimensional evaluation of the learning results. In Shanghai Gongmei teaching, the model improves the accuracy of teaching process diagnosis by 30 %, the objectivity of achievement evaluation by 35 %, and the accuracy of student growth tracking by 92 %, which proves that it can effectively promote the transformation of art design education evaluation from empirical judgment to evidence-driven paradigm.

KEYWORDS

Art design education; AI intelligent evaluation; Multimodal data; Teaching diagnosis; Education artificial intelligence

CITE THIS PAPER

Cheng Huang. AI intelligent evaluation model of art design education: teaching diagnosis method based on multi-modal data. Trends in Social Sciences and Humanities Research. 2025, 3(7): 30-33. DOI: https://doi.org/10.61784/tsshr3191.

REFERENCES

[1] Shepard L A. The role of assessment in a learning culture. Educational researcher, 2000, 29(7): 4-14. 

[2] Zhou L. Research on Evaluation of Art Education Effect in Colleges and Universities Based on Big Data Technology. Mathematical Problems in Engineering, 2022, 2022(1): 5671785.

[3] Black P, Wiliam D. Assessment and classroom learning. Assessment in Education: principles, policy & practice, 1998, 5(1): 7-74.

[4] Shang Xuyan, Li Jingxiu. Design of Digital Teaching Evaluation System Guided by OBE Concept. China Information, 2025(09): 247-249.

[5] Dong Siyu. Autonomous Course Selection Matching System. Electronic Testing, 2019(14): 63-65. DOI: 10.16520/j.cnki.1000-8519.2019.14.022.

[6] Xu Z, Yang J, Zhang H, et al. The impact of teachers' teaching strategies on students' deep learning in online learning environments: the mediating role of learning interaction. Frontiers in Education, 2025, 10:1680937. DOI: 10.3389/feduc.2025.1680937

[7] Wu J X, Li L. AI-driven computational creativity in fashion design: a review. Textile Research Journal, 2025, 95(5-6): 658-675.

[8] Chen J, Lu H. Evaluation method of classroom teaching effect under intelligent teaching mode. Mobile Networks and Applications, 2022, 27(3): 1262-1270.