This study introduces the Intelligent Support System (ISS), an integrated digital framework for digital mathematics assessment, leveraging symbolic computation, modular parametric modeling, and cognitive feedback integration via the STACK plugin on Moodle. The system automates item generation, enables real-time symbolic validation, and offers adaptive, brain-aligned feedback loops. A quasi-experimental study in Romanian secondary education demonstrated a 25.6% improvement in conceptual understanding and a 75% reduction in teacher grading workload. These findings substantiate the interdisciplinary value of integrating symbolic logic, automated process control, and neurodidactic design in scalable educational systems. By embedding engineering principles into didactic design, ISS contributes a replicable, scalable, and cognitively aligned model for next-generation STEM assessment [1–4]. Statistical results confirm a large effect size (Cohen’s d = 1.12, p < 0.001), supporting the system’s effectiveness in optimizing both performance and feedback efficiency.

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

Optimization of Symbolic Digital Assessment: A Parametric Approach Using STACK in Mathematics Education

  • Gabriela Cristina Brănoaea

摘要

This study introduces the Intelligent Support System (ISS), an integrated digital framework for digital mathematics assessment, leveraging symbolic computation, modular parametric modeling, and cognitive feedback integration via the STACK plugin on Moodle. The system automates item generation, enables real-time symbolic validation, and offers adaptive, brain-aligned feedback loops. A quasi-experimental study in Romanian secondary education demonstrated a 25.6% improvement in conceptual understanding and a 75% reduction in teacher grading workload. These findings substantiate the interdisciplinary value of integrating symbolic logic, automated process control, and neurodidactic design in scalable educational systems. By embedding engineering principles into didactic design, ISS contributes a replicable, scalable, and cognitively aligned model for next-generation STEM assessment [1–4]. Statistical results confirm a large effect size (Cohen’s d = 1.12, p < 0.001), supporting the system’s effectiveness in optimizing both performance and feedback efficiency.