Scholarlink

This study investigated the application of AI-generated prompts within the Outcome-Based Education (OBE) framework to enhance learning outcomes in an international business negotiation course. Leveraging Fink’s Taxonomy of Significant Learning, the study quantitatively compared traditional syllabus-driven learning objectives with AI-generated, personalized prompts. Using TF-IDF analysis, it evaluated the emphasis on six learning dimensions: Application, Integration, Learning How to Learn, Human Dimension, Foundational Knowledge, and Caring. Results indicated that AI-generated outcomes significantly improved in the “Application,” “Integration,” and “Learning How to Learn” dimensions, supporting hypotheses that AI-enhanced instructional design promotes flexibility, adaptability, and self-directed learning. The findings highlighted the potential of AI-driven prompts to better align with Fink’s Taxonomy, thereby advancing personalized and adaptable learning in complex, cross-cultural negotiation contexts. This study’s insights contribute to the broader integration of AI in OBE frameworks, offering empirical support for AI’s role in fostering significant learning outcomes and adaptive instruction.

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

AI-Driven Prompt Design for Learning Outcomes in International Business Negotiation: An OBE Framework Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Han Yu,
  • Yan Jun

摘要

This study investigated the application of AI-generated prompts within the Outcome-Based Education (OBE) framework to enhance learning outcomes in an international business negotiation course. Leveraging Fink’s Taxonomy of Significant Learning, the study quantitatively compared traditional syllabus-driven learning objectives with AI-generated, personalized prompts. Using TF-IDF analysis, it evaluated the emphasis on six learning dimensions: Application, Integration, Learning How to Learn, Human Dimension, Foundational Knowledge, and Caring. Results indicated that AI-generated outcomes significantly improved in the “Application,” “Integration,” and “Learning How to Learn” dimensions, supporting hypotheses that AI-enhanced instructional design promotes flexibility, adaptability, and self-directed learning. The findings highlighted the potential of AI-driven prompts to better align with Fink’s Taxonomy, thereby advancing personalized and adaptable learning in complex, cross-cultural negotiation contexts. This study’s insights contribute to the broader integration of AI in OBE frameworks, offering empirical support for AI’s role in fostering significant learning outcomes and adaptive instruction.