Integrating Narrative Learning and AI for Collaborative Problem Solving in Engineering Education Academic Article in Scopus uri icon

abstract

  • The ANECAI methodology (Narrative Learning and Collaborative AI-Assisted Assessment) integrates narrative-based instruction, cognitive scaffolding, and artificial intelligence (AI) tools to enhance learning outcomes in higher education. Grounded in problem-based learning, Bloom's taxonomy, and self-regulated learning theory, ANECAI unfolds in several phases: an initial phase of real-life contextualization, followed by theoretical development through storytelling, then scaffolded questioning, an AI-assisted synthesis phase, and finally, a collaborative peer assessment. Applied in the courses 'Chemical Experimentation and Fundamental Statistical Thinking' and 'Chemical Experimentation and Intermediate Statistical Thinking', this study employs a mixed-methods approach to assess its impact on engineering and chemistry students. Results indicate that students exposed to ANECAI achieved a 15% improvement in conceptual retention, with 94.1% reporting high levels of engagement and learning satisfaction, compared to 75% and 83.3%, respectively, in the traditional learning group. Additionally, students using ANECAI showed an 88.2% increase in self-regulated learning strategies, reinforcing its effectiveness in fostering autonomy and critical thinking. However, findings also highlight the need for additional instructional strategies to encourage deeper academic exploration and the use of complementary learning resources. These results underscore the potential of AI-driven pedagogical models in STEM education, fostering a more immersive and student-centered learning experience. © 2025 IEEE.

publication date

  • January 1, 2025