基于校园上网行为感知的学生成绩预测方法

姚丽; 崔超然; 马乐乐; 王飞超; 马玉玲; 陈勐; 尹义龙

doi:10.7544/issn1000-1239.20220060

基于校园上网行为感知的学生成绩预测方法

¹(山东大学软件学院济南 250100)
²(山东财经大学计算机科学与技术学院济南 250014)
³(齐鲁师范学院网络信息中心济南 250001)
⁴(山东建筑大学计算机科学与技术学院济南 250101) (li_yao_926@163.com)

基金项目: 国家自然科学基金项目(62077033，61876098，62177031)

详细信息

中图分类号: TP399
计量
- 文章访问数: 281
- HTML全文浏览量: 11
- PDF下载量: 198
出版历程
- 发布日期: 2022-07-31

Student Performance Prediction Base on Campus Online Behavior-Aware

¹(School of Software, Shandong University, Jinan 250100)
²(School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan 250014)
³(Network Information Center, Qilu Normal University, Jinan 250001)
⁴(School of Computer Science and Technology, Shandong Jianzhu University, Jinan 250101)

Funds: This work was supported by the National Natural Science Foundation of China (62077033, 61876098, 62177031).

摘要

摘要: 学生成绩预测旨在利用学生的相关信息预测其在未来的学业表现.随着校园信息化建设的持续推进，校园网络认证系统越来越完善，各高校逐步积累了丰富的学生校园上网行为数据.考虑到人的行为表现和学习能力密切相关，以校园上网行为感知为切入点，通过挖掘学生的上网行为日志来预测他们的成绩.为此，收集构建了一个同时包含学生校园上网行为和成绩数据的真实数据集，并通过数据分析证明两者之间确实存在一定的关联性.在此基础上，提出了一个端到端的双层自注意力网络(dual-level self-attention network, DEAN)，引入级联式的自注意力机制来分别提取学生每一天的局部上网行为特征和长时间的全局上网行为特征，更好地解决了长行为序列建模问题.此外，通过多任务学习策略在统一的框架下同时解决面向不同专业的学生成绩预测问题，并设计了基于学生排名差的代价敏感损失来进一步提升方法的性能.实验结果表明：相比于传统的序列建模方法，所提出的方法具有更好的预测精度.
- 学生成绩预测 /
- 校园上网行为感知 /
- 双层自注意力网络 /
- 多任务学习 /
- 代价敏感学习
Abstract: Student performance prediction aims to predict students’ future academic performance based on student-related information. With the growing advancement of campus IT applications, the network authentication system on campus is getting more perfect, and universities have accumulated rich data on students’ online behavior. Due to the fact that human behavior and learning ability are highly correlated, from the perspective of campus online behavior awareness, seeks to predict students’ performance by mining their online logs. To this end, we collect a real dataset consisting of both students’ online behavior and performance data, and proves the correlation between them via data analysis. On this basis, we propose an end-to-end dual-level self-attention network (DEAN), which introduces a hierarchical self-attention mechanism to separately capture the local and global characteristics of students’ daily and long-term online behavior, solving the problem of long behavior sequence modeling better. Besides, the multi-task learning is used to simultaneously conduct student performance prediction for different majors under a unified framework, and the cost-sensitive learning is designed according to the difference between students’ rankings to further improve the method performance. Experimental results demonstrate that the proposed method can make more accurate predictions in comparison with the traditional sequence modeling methods.
- student performance prediction /
- campus online behavior awareness /
- dual-level self-attention network /
- multi-task learning /
- cost-sensitive learning

HTML全文

参考文献(0)

施引文献(16)

期刊类型引用(4)

1.	钱罗雄，陈梅，马学艳，张弛，张锦宏. 自适应张量奇异值收缩的多视角聚类. 计算机研究与发展. 2025(03): 733-750 . 本站查看
2.	赵兴旺，侯哲栋，姚凯旋，梁吉业. 基于注意力机制的两阶段融合多视图图聚类. 清华大学学报(自然科学版). 2024(01): 1-12 . 百度学术
3.	赵振廷，赵旭俊. 多样性约束和高阶信息挖掘的多视图聚类. 计算机应用研究. 2024(08): 2309-2314 . 百度学术
4.	李顺勇，许晓丽. 基于信息熵加权的多视图子空间聚类算法. 陕西科技大学学报. 2023(02): 207-214 . 百度学术