[1]张文娟,张 彬,杨皓哲.基于双注意力机制的成绩预测[J].南京师大学报(自然科学版),2023,46(04):103-113.[doi:10.3969/j.issn.1001-4616.2023.04.014]
　Zhang Wenjuan,Zhang Bin,Yang Haozhe.Performance Prediction based on Dual-Attention Mechanism[J].Journal of Nanjing Normal University(Natural Science Edition),2023,46(04):103-113.[doi:10.3969/j.issn.1001-4616.2023.04.014]
点击复制

基于双注意力机制的成绩预测()
分享到：

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

卷:
第46卷
期数:
2023年04期
页码:
103-113
栏目:
计算机科学与技术
出版日期:
2023-12-15

文章信息/Info

Title:
Performance Prediction based on Dual-Attention Mechanism
文章编号:
1001-4616(2023)04-0103-11
作者:
张文娟; 张 彬; 杨皓哲
(同济大学机械与能源工程学院,上海 201800)
Author(s):
Zhang Wenjuan; Zhang Bin; Yang Haozhe
(School of Mechanical Engineering,Tongji University,Shanghai 201800,China)
关键词:
计算机应用; 虚拟学习环境; 成绩预测; 反馈时间; 注意力机制; 神经网络
Keywords:
computer application;  virtual learning environment;  performance prediction;  feedback time;  attention mechanism;  neural networks
分类号:
TP391
DOI:
10.3969/j.issn.1001-4616.2023.04.014
文献标志码:
A
摘要:
为更好利用虚拟学习环境中的数据,提升学习者成绩和教师教学效果,准确预测学习者的成绩、确定重要影响因素以及确定合适的反馈时间点这三项工作非常重要. 本文基于问题域的形式化描述,在明确研究对象特征和假设条件后,提出了一种集成了双注意力机制、门控循环单元(gated recurrent unit,GRU)与一维卷积神经网络(convolutional neural networks,CNN)的网络模型,并在两个公开数据集上进行实验验证. 结果显示该模型可以有效实现上述三个核心功能,且在寻找合适的反馈时间时比目前主流方法更为快捷,结果更具普遍性.
Abstract:
In order to make better use of the data in the virtual learning environment and improve the performance of learners and the teaching effect,a neural network integrating the dual-attention mechanism GRU(Gated Recurrent Unit)and one-dimensional CNN(Convolutional Neural Networks)was proposed. First,formalized description of the problem domain is given,and some assumptions about the research object are determined. Then,according to the three core functions of the problem,learners' performance prediction,the determination of important influencing factors and the determination of feedback time,a neural network model is constructed. Finally,the experimental results on two public data sets show that the proposed model can effectively realize the three core functions. In addition,it is faster than the current mainstream methods in determining the feedback time,and the results are more general.

参考文献/References:

[1]CHEN F,CUI Y. Utilizing student time series behaviour in learning management systems for early prediction of course performance[J]. Journal of learning analytics,2020,7(2):1-17.
[2]OKUBO F,YAMASHITA T,SHIMADA A,et al. On the prediction of students' quiz score by recurrent neural network[J]. CrossMMLA@LAK,2018,102.
[3]PANDEY M,SHARMA V K. A decision tree algorithm pertaining to the student performance analysis and prediction[J]. International journal of computer applications,2013,61(13):1-5.
[4]OKUBO F,YAMASHITA T,SHIMADA A,et al. A neural network approach for students' performance prediction[C]//Proceedings of the Seventh International Learning Analytics & Knowledge Conference. New York:ACM,2017:598-599.
[5]LU O H T,HUANG A Y Q,HUANG J C H,et al. Applying learning analytics for the early prediction of Students' academic performance in blended learning[J]. Journal of educational technology & society,2018,21(2):220-232.
[6]AYDO AGˇU1 DU . Predicting student final performance using artificial neural networks in online learning environments[J]. Education and information technologies,2020,25(3):1913-1927.
[7]李梦莹,王晓东,阮书岚,等. 基于双路注意力机制的学生成绩预测模型[J]. 计算机研究与发展,2020,57(8):1729-1740.
[8]HASSAN S U,WAHEED H,ALJOHANI N R,et al. Virtual learning environment to predict withdrawal by leveraging deep learning[J]. International journal of intelligent systems,2019,34(8):1935-1952.
[9]杜欣远. 基于校园网数据的学习行为分析及学业预警技术的研究与实现[D]. 北京:北京邮电大学,2020.
[10]WAHEED H,HASSAN S U,ALJOHANI N R,et al. Predicting academic performance of students from VLE big data using deep learning models[J]. Computers in human behavior,2020,104:106189.
[11]BAKER R. Data mining for education[J]. International encyclopedia of education,2010,7(3):112-118.
[12]张永峰,陆志强. 基于集成神经网络的剩余寿命预测[J]. 工程科学学报,2020,42(10):1372-1380.
[13]KUZILEK J,HLOSTA M,ZDRAHAL Z. Open university learning analytics dataset[J]. Scientific data,2017,4(1):1-8.
[14]HEUER H,BREITER A. Student success prediction and the trade-off between big data and data minimization[J]. DeLFI 2018-Die 16. E-Learning Fachtagung Informatik,2018.
[15]孙小雪,钟辉,陈海鹏.基于决策树分类技术的学生考试成绩统计分析系统[J]. 吉林大学学报(工学版),2021,51(5):1866-1872.
[16]HLOSTA M,ZDRAHAL Z,ZENDULKA J. Ouroboros:early identification of at-risk students without models based on legacy data[C]//Proceedings of the Seventh International Learning Analytics & Knowledge Conference. New York:ACM,2017:6-15.
[17]AMRIEH E A,HAMTINI T,ALJARAH I. Mining educational data to predict student's academic performance using ensemble methods[J]. International journal of database theory and application,2016,9(8):119-136.

备注/Memo

备注/Memo:
收稿日期:2022-11-18.
基金项目:大型交通枢纽智能协同运营关键技术研究与示范(21DZ1203700).
通讯作者:张文娟,博士,副研究员,研究方向:智能服务质量评价、高等工程教育. E-mail:a8222436711@126.com
更新日期/Last Update: 2023-12-15