EMPIRICAL RESEARCH ON THE CROSS-CONTEXT ADAPTABILITY OF THE FIVE-ELEMENT SYNERGISTIC MODEL IN HIGHER EDUCATION: A MULTI-DIMENSIONAL TEST BASED ON DISCIPLINES, INSTITUTIONS, AND REGIONS

Against the backdrop of global sustainable education transformation and rapid AI integration, the cross-context adaptability of educational models has become a key prerequisite for their large-scale promotion. Based on contextual adaptation theory, complex systems theory, and Education for Sustainable Development (ESD) principles, this study takes the "Faculty-Student-AI-Environment-Culture" five-element synergistic model as the research object, adopting a sequential explanatory mixed-methods design to explore its adaptability across different disciplines, institution types, regions, and demographic groups. A total of 431 valid questionnaires (covering 3 disciplines, 3 institution types, and 3 socio-economic regions in China) and 42 semi-structured interviews were collected. The data were analyzed using one-way ANOVA, two-way ANOVA, post-hoc tests, and thematic analysis. The results show that: (1) The five-element synergistic model has strong cross-disciplinary adaptability, with no significant differences in synergy levels across Science & Engineering (STEM), Humanities & Social Sciences (HSS), and Economics & Management (E&M) disciplines (F=0.635, p=0.530, η²≈0.003); (2) The model exhibits good cross-institutional generalizability, with no significant differences among Comprehensive, STEM, and HSS institutions (F=0.249, p=0.779, η²≈0.001); (3) Regional differences are significant: the synergy level in Eastern China (M=3.75, SD=0.45) is significantly higher than that in Western China (M=3.56, SD=0.48) (p=0.028); (4) Faculty age groups show significant differences: young faculty (M=3.78, SD=0.42) have significantly higher synergy levels than senior faculty (M=3.52, SD=0.51) (p=0.021); (5) Qualitative analysis reveals that the universal adaptability of the model stems from the core elements’ alignment with the fundamental needs of higher education, while contextual differences are driven by resource allocation, technological acceptance, and institutional culture. This study verifies the model’s broad generalizability and identifies key contextual moderators, providing evidence-based guidance for targeted promotion strategies of AI-integrated sustainable education across different contexts, and enriching the theoretical system of cross-context adaptation in educational models.