Scholarlink

<p>The introduction of Artificial Intelligence (AI) in higher education has opened up opportunities in the history of studying in the classroom and has been able to implement the most successful reform strategies, but the selection of the most effective ones is a complicated issue because of a variety of conflicting criteria and the unpredictability of expert opinion. This paper proposes a q-rung orthopair fuzzy RANking COMparison Faire Un Choix Adéquat (qROF-RANCOM-FUCA) decision model to critically evaluate AI-supported classroom teaching changes. The q-rung orthopair fuzzy sets (qROFSs) framework can effectively handle uncertainty, vagueness, and hesitation in expert judgment. The RANCOM approach uses weightings of criteria according to knowledge of the experts (subjective knowledge). In contrast, the FUCA method uses weightings of the alternatives to balance conflicting criteria without normalizing the information. The approach is illustrated in a hypothetical case study of ten teaching strategies using AI and seven assessment criteria, incalgorithm for finding the values that are presented in the element is as followsluding teaching effectiveness, student engagement, personalization, compatibility with the infrastructure, data-driven decision support, innovation, and the cost of implementation. Findings show that AI-Enhanced Collaborative Learning Platforms achieved the highest preference value, followed by Personalized Learning Path Systems, demonstrating superior performance among the ten evaluated strategies. Moreover, the proposed qROF-RANCOM-FUCA framework produced more stable ranking results and stronger discriminative capability compared with existing qROF multi-criteria decision-making (MCDM) methods. Sensitivity analysis has demonstrated that these systems are robust across different fuzzy parameters. It has better accuracy, consistency, and discriminative power than current qROF MCDM methods. The suggested framework is a valid and practical tool that administrators and policymakers can use to implement successful AI-based teaching reforms in higher education.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluating Artificial Intelligence enabled teaching reform in higher education using the generalized orthopair fuzzy RANCOM FUCA decision framework

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月28日

查看全文
  • Zhaobin Xu,
  • Hongfeng Xu,
  • Mei Yang,
  • Pufan Zhao

摘要

The introduction of Artificial Intelligence (AI) in higher education has opened up opportunities in the history of studying in the classroom and has been able to implement the most successful reform strategies, but the selection of the most effective ones is a complicated issue because of a variety of conflicting criteria and the unpredictability of expert opinion. This paper proposes a q-rung orthopair fuzzy RANking COMparison Faire Un Choix Adéquat (qROF-RANCOM-FUCA) decision model to critically evaluate AI-supported classroom teaching changes. The q-rung orthopair fuzzy sets (qROFSs) framework can effectively handle uncertainty, vagueness, and hesitation in expert judgment. The RANCOM approach uses weightings of criteria according to knowledge of the experts (subjective knowledge). In contrast, the FUCA method uses weightings of the alternatives to balance conflicting criteria without normalizing the information. The approach is illustrated in a hypothetical case study of ten teaching strategies using AI and seven assessment criteria, incalgorithm for finding the values that are presented in the element is as followsluding teaching effectiveness, student engagement, personalization, compatibility with the infrastructure, data-driven decision support, innovation, and the cost of implementation. Findings show that AI-Enhanced Collaborative Learning Platforms achieved the highest preference value, followed by Personalized Learning Path Systems, demonstrating superior performance among the ten evaluated strategies. Moreover, the proposed qROF-RANCOM-FUCA framework produced more stable ranking results and stronger discriminative capability compared with existing qROF multi-criteria decision-making (MCDM) methods. Sensitivity analysis has demonstrated that these systems are robust across different fuzzy parameters. It has better accuracy, consistency, and discriminative power than current qROF MCDM methods. The suggested framework is a valid and practical tool that administrators and policymakers can use to implement successful AI-based teaching reforms in higher education.