In online education platforms, accurately predicting student performance is essential for timely dropout prevention and interventions for at-risk students. This task is made difficult by the prevalent use of Multiple-Choice Questions (MCQs) in learnersourcing platforms, where noise in student-generated content and the limitations of existing unsigned graph-based models, specifically their inability to distinguish the semantic meaning between correct and incorrect responses, hinder accurate performance predictions. To address these issues, we introduce the arge anguage odel enhanced igned ipartite graph ontrastive earning (LLM-SBCL) model—a novel Multimodal Model utilizing Signed Graph Neural Networks (SGNNs) and a Large Language Model (LLM). Our model uses a signed bipartite graph to represent students’ answers, with positive and negative edges denoting correct and incorrect responses, respectively. To mitigate noise impact, we apply contrastive learning to the signed graphs, combined with knowledge point embeddings from the LLM to further enhance our model’s predictive performance. Upon evaluating our model on five real-world datasets, it demonstrates superior accuracy and stability, exhibiting an average F1 improvement of 3.7% over the best baseline models.

中文翻译：

---

学生表现的多模态预测：符号图神经网络和大型语言模型的融合

在在线教育平台中，准确预测学生的表现对于及时预防辍学和对高危学生进行干预至关重要。这项任务因学习者采购平台中普遍使用多项选择题 (MCQ) 而变得困难，其中学生生成的内容中存在噪音，并且现有基于无符号图的模型存在局限性，特别是它们无法区分正确和正确之间的语义。不正确的响应会阻碍准确的性能预测。为了解决这些问题，我们引入了大语言模型增强型有符号分图对比收益（LLM-SBCL）模型——一种利用符号图神经网络（SGNN）和大语言模型（LLM）的新型多模态模型。我们的模型使用带符号的二分图来表示学生的答案，正边和负边​​分别表示正确和错误的答案。为了减轻噪声影响，我们将对比学习应用于签名图，并结合法学硕士的知识点嵌入，以进一步增强模型的预测性能。在五个真实数据集上评估我们的模型后，它表现出了卓越的准确性和稳定性，与最佳基线模型相比，平均 F1 提高了 3.7%。