Game-based learning (GBL) is widely adopted in mathematics education. It enhances learners' engagement and critical thinking throughout the mathematics learning process. However, enabling players to learn intrinsically through mathematical games still presents challenges. In particular, effective GBL systems require dozens of high-quality game levels and mechanisms to deliver them to appropriate players in a way that matches their learning abilities. To address this challenge, we propose a framework, guided by adaptive learning theory, that uses artificial intelligence (AI) techniques to build a classifier for player-generated levels. We collect 206 distinct game levels created by both experts and advanced players in Creative Mode, a new tool in a math game-based learning app, and develop a classifier to extract game features and predict valid game levels. The preliminary results show that the Random Forest model is the optimal classifier among the four machine learning classification models (k-nearest neighbors, decision trees, support vector machines, and random forests). This study provides insights into the development of GBL systems, highlighting the potential of integrating AI into the game-level design process to provide more personalized game levels for players.

翻译：游戏化学习（GBL）在数学教育中已被广泛应用。它能在整个数学学习过程中提升学习者的参与度和批判性思维能力。然而，使玩家能够通过数学游戏进行内在学习仍面临挑战。具体而言，有效的GBL系统需要数十个高质量的游戏关卡，以及相应的机制，将这些关卡以匹配玩家学习能力的方式分发给合适的玩家。为解决这一难题，我们提出了一个以自适应学习理论为指导的框架，利用人工智能（AI）技术构建针对玩家自创关卡的分类器。我们收集了专家和高阶玩家在一款数学游戏化学习应用的“创造模式”（一种新工具）中创建的206个不同的游戏关卡，并开发了一个分类器来提取游戏特征并预测有效游戏关卡。初步结果显示，在四种机器学习分类模型（k-近邻、决策树、支持向量机和随机森林）中，随机森林模型是最优分类器。本研究为GBL系统的开发提供了见解，强调了将AI整合到游戏关卡设计过程中，从而为玩家提供更个性化游戏关卡的潜力。