状态焦虑是人对外部压力源的短暂反应。在课堂情境中，长期处于严重的状态焦虑水平会显著影响学生的身心健康，严重时甚至导致自杀想法的产生。学生状态焦虑水平的准确识别是保护学生心理健康的重要一环。

尽管基于视频的状态焦虑评估方法取得了一定进展，但数据和线索方面的挑战仍然限制了其的评估性能。首先，以往的训练数据主要面向通用群体，缺乏学生领域的数据集。其次，单个视频提供的线索有限，当学生在视频中一直维持中性表情时，评估方法难以做出准确判断。

为了应对数据方面的挑战，本研究收集了首个包含106名学生的3701段视频的状态焦虑数据集，每段视频都标注了学生真实的状态焦虑水平。此外，为了解决线索方面的挑战，本研究构建了一个面向状态焦虑的知识图，并提出了一种基于图的学生状态焦虑评估方法。具体为，本研究将课程信息、事件信息、学生的学业和心理健康状态，以及视频之间的隐含关联作为线索添加到图中，并在评估方法中设计了三个注意模块来融合这些线索以提高评估性能。

在所收集的数据集上，实验结果表明，本研究方法在评估学生状态焦虑方面具有极高的准确性，误差极小（均方误差为0.1380，平均绝对误差为0.2768）。

State anxiety is a temporary reaction to external stressors. In classroom scenarios, severe state anxiety over a long period significantly affects the physical and mental health of school students, potentially leading to suicidal thoughts in extreme cases. Accurately identifying students' state anxiety levels is a crucial component in protecting their mental health.

Researchers often use students' facial videos to assess their state anxiety. However, video-based assessment methods face challenges with data and clues, limiting their effectiveness in assessing student state anxiety. First, previous datasets mainly focused on the general population and there was a lack of a domain-specific dataset. Second, a single video provides limited clues, making it challenging for assessment methods to make accurate judgments when the student consistently displays a neutral expression.

To address the data challenge, we collected the first state anxiety dataset containing 3,701 video clips from 106 school students. To solve the clue challenge, we constructed a student-level state-anxiety-oriented graph and proposed a graph-based assessment method for student state anxiety. This method incorporates course information, event information, students' academic and mental health statuses, and the implicit correlations between videos. Three well-designed attention modules were used to fuse these clues for better performance.

Experimental results on the collected dataset demonstrate that our method is highly accurate in assessing students' state anxiety, with minimal errors (MSE=0.1380, MAE=0.2768).