In the Massive Online Open Course (MOOC) forum, learning engagement encompasses three fundamental dimensions—cognitive, emotional, and behavioral engagement—that intricately interact to jointly influence students' learning achievements. However, the interplay between multiple engagement dimensions and their correlations with learning achievement remain understudied, particularly across different academic disciplines. This study adopts an automated configurational approach that integrates bidirectional encoder representation from transformers (BERT) and fuzzy set qualitative comparative analysis (fsQCA) to explore the configurations of learning engagement, their connections with learning achievement, and variations across disciplines. Our analysis reveals a nuanced profile of learners' learning engagement, indicating the high-achieving individuals demonstrated more frequent posting and commenting behaviors and the high-level cognitive engagement than low-achieving individuals. Second, our analysis revealed multiple configurations where the coexistence or absence of factors at different levels of the cognitive, behavioral, and emotional dimensions significantly impacted learning achievement. Learners who conducted posting and replying behaviors, expressed positive emotions, and engaged in deep cognitive engagement tended to achieve superior learning outcomes. Third, there were significant differences in behavioral and emotional engagement among learners across different academic disciplines. Specifically, pure discipline learners were more inclined to engage in postin behaviors than the applied discipline learners. Across academic disciplines, positive emotions correlated strongly with higher achievement. These findings deepen our understanding of the multifaceted characteristics of learning engagement in MOOCs and highlight the importance of disciplinary distinctions, providing a foundation for educators and designers to optimize learners’ MOOC effects and tailor learning experiences in diverse disciplinary contexts.

中文翻译：

---

分析学生在 MOOC 讨论中的学习参与情况，以确定学习成绩：一种自动配置方法


在大规模在线开放课程（MOOC）论坛中，学习投入包含认知投入、情感投入和行为投入三个基本维度，它们错综复杂地相互作用，共同影响学生的学习成果。然而，多个参与维度之间的相互作用及其与学习成绩的相关性仍未得到充分研究，特别是在不同的学科领域。本研究采用自动化配置方法，集成了来自 Transformer 的双向编码器表示 (BERT) 和模糊集定性比较分析 (fsQCA)，以探索学习参与的配置、它们与学习成绩的联系以及跨学科的变化。我们的分析揭示了学习者学习投入的细微差别，表明成绩优异的个体比成绩低下的个体表现出更频繁的发帖和评论行为以及高水平的认知投入。其次，我们的分析揭示了多种配置，其中认知、行为和情感维度不同层面的因素的共存或缺失显着影响学习成绩。进行发帖和回复行为、表达积极情绪并进行深度认知参与的学习者往往会取得优异的学习成果。第三，不同学科的学习者的行为和情感投入存在显着差异。具体而言，纯学科学习者比应用学科学习者更倾向于从事事后行为。在各个学科中，积极情绪与更高的成就密切相关。 这些发现加深了我们对 MOOC 学习参与的多方面特征的理解，并强调了学科区别的重要性，为教育工作者和设计者提供了基础，以优化学习者的 MOOC 效果并在不同学科背景下定制学习体验。