DPOTS: eXplainable Artificial Intelligence Dataset for Predicting Outcomes from Time Sequences and Student Behaviors

DPOTS: eXplainable Artificial Intelligence (XAI) Dataset for Predicting Outcomes from Time Sequences and Student Behaviors Accurately and timely predicting learners' outcomes can assist educators in making instructional decisions or interventions. This helps prevent students from falling into a vicious cycle of decreased academic achievement and increased aversion to learning, potentially leading to dropout. Data-driven models often outperform eXplainable Artificial Intelligence (XAI) models in predicting learning outcomes, yet their lack of interpretability can hinder trust from educators. Therefore, this study developed an XAI information fusion framework that not only extracts potential trends from the time series of student grades to enhance predictive performance but also mines explicit relationships between classroom behaviors and learning outcomes. This reveals the behavioral causes behind changes in grades. Furthermore, we have made public the Dataset for Predicting Outcomes from Time sequences and Student behaviors (DPOTS), and validated the effectiveness of the developed XAI information fusion framework based on DPOTS. The results indicate that, the MAE of CEO-IF was reduced by an average of 26.32% compared to the baseline algorithms, and it showed a 22.63% reduction compared to the averaging-based information fusion method. Copyright The Copyright of the DPOTS belongs to the authors and their affiliates. You are free to use DPOTS for research purposes. The authors is not responsible for any consequences of the user's use of the data or code. Papers containing data generated using the data or code should declare the use of the DPOTS , and cite the corresponding references correctly: Code: https://doi.org/10.5281/zenodo.14958102 Paper: https://doi.org/10.1145/3706599.3721212 Support According to ethical requirements, if you need to access this data, please send an email to Zi Wei Chen to apply. If you have any comments or suggestions, please contact [e-mail] (Zi-Wei Chen). Finally, thank you again for using DPOTS.DPOTS：面向时序与学生行为结果预测的可解释人工智能（XAI）数据集 准确且及时地预测学习者的学习成果，能够辅助教育工作者制定教学决策或实施干预措施，从而避免学生陷入学业成绩下滑、学习厌恶感加剧的恶性循环——此类循环可能最终导致学生辍学。数据驱动模型在学习成果预测任务中往往表现优于可解释人工智能（eXplainable Artificial Intelligence, XAI）模型，但由于缺乏可解释性，难以获得教育工作者的信任。因此，本研究构建了一种XAI信息融合框架，该框架不仅能够从学生成绩的时序序列中提取潜在趋势以提升预测性能，还能挖掘课堂行为与学习成果之间的显性关联，进而揭示成绩变化背后的行为成因。此外，本研究公开了面向时序与学生行为结果预测的数据集（DPOTS），并基于该数据集验证了所提出的XAI信息融合框架的有效性。实验结果表明，CEO-IF的平均绝对误差（Mean Absolute Error, MAE）较基线算法平均降低了26.32%，较基于平均的信息融合方法降低了22.63%。 版权 DPOTS的著作权归属于本研究作者及其所属机构。您可出于科研目的自由使用DPOTS。作者不对用户使用该数据或代码所产生的任何后果承担责任。若您的论文中使用了本数据集或基于本数据集生成的数据，请声明使用了DPOTS，并正确引用以下参考文献： 代码：https://doi.org/10.5281/zenodo.14958102 论文：https://doi.org/10.1145/3706599.3721212 支持与申请 根据伦理规范要求，若您需要获取该数据集，请发送邮件至陈子薇（Zi Wei Chen）进行申请。若您有任何意见或建议，请联系[e-mail]（陈子薇）。最后，再次感谢您使用DPOTS。