通过学生表征重构和班级失衡缓解个性化知识追踪

Zhiyu Chen, Wei Ji, Jing Xiao, Zitao Liu
{"title":"通过学生表征重构和班级失衡缓解个性化知识追踪","authors":"Zhiyu Chen, Wei Ji, Jing Xiao, Zitao Liu","doi":"arxiv-2409.06745","DOIUrl":null,"url":null,"abstract":"Knowledge tracing is a technique that predicts students' future performance\nby analyzing their learning process through historical interactions with\nintelligent educational platforms, enabling a precise evaluation of their\nknowledge mastery. Recent studies have achieved significant progress by\nleveraging powerful deep neural networks. These models construct complex input\nrepresentations using questions, skills, and other auxiliary information but\noverlook individual student characteristics, which limits the capability for\npersonalized assessment. Additionally, the available datasets in the field\nexhibit class imbalance issues. The models that simply predict all responses as\ncorrect without substantial effort can yield impressive accuracy. In this\npaper, we propose PKT, a novel approach for personalized knowledge tracing. PKT\nreconstructs representations from sequences of interactions with a tutoring\nplatform to capture latent information about the students. Moreover, PKT\nincorporates focal loss to improve prioritize minority classes, thereby\nachieving more balanced predictions. Extensive experimental results on four\npublicly available educational datasets demonstrate the advanced predictive\nperformance of PKT in comparison with 16 state-of-the-art models. To ensure the\nreproducibility of our research, the code is publicly available at\nhttps://anonymous.4open.science/r/PKT.","PeriodicalId":501112,"journal":{"name":"arXiv - CS - Computers and Society","volume":"23 13 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Personalized Knowledge Tracing through Student Representation Reconstruction and Class Imbalance Mitigation\",\"authors\":\"Zhiyu Chen, Wei Ji, Jing Xiao, Zitao Liu\",\"doi\":\"arxiv-2409.06745\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Knowledge tracing is a technique that predicts students' future performance\\nby analyzing their learning process through historical interactions with\\nintelligent educational platforms, enabling a precise evaluation of their\\nknowledge mastery. Recent studies have achieved significant progress by\\nleveraging powerful deep neural networks. These models construct complex input\\nrepresentations using questions, skills, and other auxiliary information but\\noverlook individual student characteristics, which limits the capability for\\npersonalized assessment. Additionally, the available datasets in the field\\nexhibit class imbalance issues. The models that simply predict all responses as\\ncorrect without substantial effort can yield impressive accuracy. In this\\npaper, we propose PKT, a novel approach for personalized knowledge tracing. PKT\\nreconstructs representations from sequences of interactions with a tutoring\\nplatform to capture latent information about the students. Moreover, PKT\\nincorporates focal loss to improve prioritize minority classes, thereby\\nachieving more balanced predictions. Extensive experimental results on four\\npublicly available educational datasets demonstrate the advanced predictive\\nperformance of PKT in comparison with 16 state-of-the-art models. To ensure the\\nreproducibility of our research, the code is publicly available at\\nhttps://anonymous.4open.science/r/PKT.\",\"PeriodicalId\":501112,\"journal\":{\"name\":\"arXiv - CS - Computers and Society\",\"volume\":\"23 13 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computers and Society\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.06745\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computers and Society","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06745","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

知识追踪是一种通过分析学生与智能教育平台的历史互动来预测其未来表现的技术,可以对学生的知识掌握情况进行精确评估。最近的研究利用强大的深度神经网络取得了重大进展。这些模型利用问题、技能和其他辅助信息构建复杂的输入表示,但忽略了学生的个体特征,从而限制了个性化评估的能力。此外,该领域现有的数据集还存在班级不平衡的问题。那些不费吹灰之力就能预测所有回答正确的模型可能会产生令人印象深刻的准确性。在本文中,我们提出了 PKT,一种用于个性化知识追踪的新方法。PKT 从与辅导平台的交互序列中构建表征,以捕捉学生的潜在信息。此外,PKT还结合了焦点损失(focal loss)来提高少数群体的优先级,从而实现更均衡的预测。在四个公开的教育数据集上进行的大量实验结果表明,与 16 个最先进的模型相比,PKT 的预测性能更胜一筹。为了确保我们研究的可重复性,我们在https://anonymous.4open.science/r/PKT 上公开了代码。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Personalized Knowledge Tracing through Student Representation Reconstruction and Class Imbalance Mitigation
Knowledge tracing is a technique that predicts students' future performance by analyzing their learning process through historical interactions with intelligent educational platforms, enabling a precise evaluation of their knowledge mastery. Recent studies have achieved significant progress by leveraging powerful deep neural networks. These models construct complex input representations using questions, skills, and other auxiliary information but overlook individual student characteristics, which limits the capability for personalized assessment. Additionally, the available datasets in the field exhibit class imbalance issues. The models that simply predict all responses as correct without substantial effort can yield impressive accuracy. In this paper, we propose PKT, a novel approach for personalized knowledge tracing. PKT reconstructs representations from sequences of interactions with a tutoring platform to capture latent information about the students. Moreover, PKT incorporates focal loss to improve prioritize minority classes, thereby achieving more balanced predictions. Extensive experimental results on four publicly available educational datasets demonstrate the advanced predictive performance of PKT in comparison with 16 state-of-the-art models. To ensure the reproducibility of our research, the code is publicly available at https://anonymous.4open.science/r/PKT.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信