Machine learning was applied to examine whether stress-related factors influence student performance in a consistent way across the world. The main goal of this project is to confirm or reject the existence of a similar global pattern by generalizing the findings that already exist in this field. We focused on various psychological indicators such as anxiety score, test anxiety, math anxiety, math confidence, wellbeing, and sense of belonging, along with several non-psychological factors for context. Machine learning was chosen due to the extremely large size of the PISA 2022 dataset and its ability to capture complex relationships that simpler methods may overlook. The analysis was conducted across six continents by splitting the dataset into six separate case studies. Feature engineering was performed manually for each region, while the same baseline models were trained to ensure a fair comparison. The results show that the negative effect of stress on performance is present and fairly consistent across all continents. Although some error remains, partly because stress is not the only factor shaping academic outcomes, the overall pattern is clear. Africa stood out as an outlier due to lower average educational and wellbeing levels and a higher proportion of missing data, yet even there the negative relationship remained observable.

翻译：本研究运用机器学习方法，检验压力相关因素是否在全球范围内以一致方式影响学生学业表现。项目主要目标是通过总结该领域已有研究成果，确认或否定全球性相似模式的存在。我们重点关注焦虑评分、考试焦虑、数学焦虑、数学自信、幸福感、归属感等多种心理指标，并结合若干非心理情境因素进行分析。鉴于PISA 2022数据集规模极其庞大，且机器学习能捕捉简单方法可能忽略的复杂关系，本研究选择了该技术路线。分析覆盖六大洲，将数据集划分为六个独立案例研究。对各地区分别进行人工特征工程，同时训练相同的基线模型以确保公平比较。结果表明，压力对学业表现的负面影响在所有大洲普遍存在且具有相当一致性。尽管存在部分误差（部分原因在于学业成绩并非仅受压力单一因素影响），但整体模式清晰可辨。非洲作为异常值出现——其教育水平与幸福感均值较低且缺失数据比例较高——然而即便在此区域，这一负相关关系仍可观测。