Building and Using State-Anxiety-Oriented Graph for Student State Anxiety Assessment in Online Classroom Scenarios

State anxiety is a temporary reaction to external stressors. In online classroom scenarios, severe state anxiety over a long period significantly affects the physical and mental health of high school students. Researchers often use students' facial videos to assess their state anxiety. However, videobased 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 high school students. To solve the clue challenge, we constructed a student-level stateanxiety-oriented graph and proposed a graph-based assessment method for student state anxiety at the video-level. This method incorporates course information, event information, students' academic and mental health statuses, and the earlier video information. Three well-designed attention modules are 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).