Scholarlink

We present an adaptive system that generates and evaluates propositional logic exercises based on student profiles. By combining Answer Set Programming (DLV) with Python coordination, the system adapts difficulty, provides real-time feedback, and updates learner models. Grounded in Mastery Learning and Cognitive Load Theory, it aims to foster conceptual reasoning and reduce cognitive overload. Preliminary results suggest improved accuracy and engagement, supporting its potential as a scalable tool for logic education.

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

An Adaptive System for Generating and Evaluating Propositional Logic Exercises Based on Student Profiles

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Gabriel Cervantes,
  • Luciano Martínez-Balbuena,
  • Mauricio Osorio,
  • Miguel Pérez-Gaspar,
  • Juan Manuel Ramírez-Contreras

摘要

We present an adaptive system that generates and evaluates propositional logic exercises based on student profiles. By combining Answer Set Programming (DLV) with Python coordination, the system adapts difficulty, provides real-time feedback, and updates learner models. Grounded in Mastery Learning and Cognitive Load Theory, it aims to foster conceptual reasoning and reduce cognitive overload. Preliminary results suggest improved accuracy and engagement, supporting its potential as a scalable tool for logic education.