Learner satisfaction is a critical quality signal in massive open online courses (MOOCs), directly influencing retention, engagement, and platform reputation. Most existing methods infer satisfaction \emph{post hoc} from end-of-course reviews and star ratings, which are too late for effective intervention. In this paper, we study \textbf{early-warning satisfaction forecasting}: predicting a learner's eventual satisfaction score using only signals observed in the first $t$ days of a course (e.g., $t\!\in\!\{7, 14, 28\}$). We propose \textbf{TET-LLM}, a multi-modal fusion framework that combines (i) a \emph{temporal event Transformer} over fine-grained behavioral event sequences, (ii) \emph{LLM-based contextual embeddings} extracted from early textual traces such as forum posts and short feedback, and (iii) short-text \emph{topic/aspect distributions} to capture coarse satisfaction drivers. A heteroscedastic regression head outputs both a point estimate and a predictive uncertainty score, enabling conservative intervention policies. Comprehensive experiments on a large-scale multi-platform MOOC dataset demonstrate that TET-LLM consistently outperforms aggregate-feature and text-only baselines across all early-horizon settings, achieving an RMSE of 0.82 and AUC of 0.77 at the 7-day horizon. Ablation studies confirm the complementary contribution of each modality, and uncertainty calibration analysis shows near-nominal 90\% interval coverage.

翻译：学习者满意度是大规模开放在线课程（MOOC）中衡量质量的关键信号，直接影响用户留存、参与度及平台声誉。现有方法大多依赖课程结束后的评论与星级评分进行事后推断，此时已无法实施有效干预。本文研究**满意度早期预警预测**：仅利用课程开始后前$t$天（如$t\in\{7,14,28\}$）可观测信号，预测学习者的最终满意度评分。我们提出**TET-LLM**多模态融合框架，该框架融合三种模态：（i）基于细粒度行为事件序列的**时序事件Transformer**，（ii）从论坛帖子和简短反馈等早期文本痕迹中提取的**大语言模型上下文嵌入**，以及（iii）用于捕捉粗粒度满意度驱动因素的短文本**主题/方面分布**。采用异方差回归头同时输出点估计值和预测不确定性分数，支持制定保守型干预策略。在跨平台大规模MOOC数据集上的全面实验表明，TET-LLM在所有早期预测时间节点均持续优于基于聚合特征和纯文本的基线方法，在7天节点上实现了0.82的RMSE（均方根误差）与0.77的AUC（曲线下面积）。消融研究证实了各模态的互补贡献，不确定性校准分析显示区间覆盖率接近理论90%名义水平。