ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Progressive knowledge tracing: Modeling learning process from abstract to concrete

Sun, Jianwen; Wei, Mengqi; Feng, Jintian; Yu, Fenghua; Li, Qing; Zou, Rui*cent china normal univ
EXPERT SYSTEMS WITH APPLICATIONS2024-3-15DOI: 10.1016/j.eswa.2023.122280
12阅读
引用收藏
分享

摘要

Artificial intelligence has the potential to revolutionize education by providing personalized learning experi-ences that support the dream of "teaching students according to their aptitude". Knowledge tracing (KT) is a critical research topic in intelligent education and is a powerful tool for achieving AI-assisted education. Both the learning process and the response result are important for KT. However, existing KT methods rarely employ a stage-based modeling approach to dissect the learning process. We propose Progressive Knowledge Tracing (PKT), which models the learning process in stages. PKT decomposes the learning process into three relatively independent but progressively related stages: concept mastery, question solving, and answering behavior. Inspired by constructivist learning theory and item response theory, PKT incorporates interpretable parameters with educational significance. Compared with existing KT methods, this staged modeling method that integrates educational theory has more reasonable interpretability. Experiments on six real-world datasets demonstrate that PKT outperforms baseline methods. Several experiments show that PKT reasonably models the learning process. For example, it more reasonably estimates the trend of concept mastery over time, analyzes the reasons why learners make mistakes on specific questions, and provides estimates of question difficulty that are closer to reality. We also find the intuitive phenomenon that the difficulty of a question is positively correlated with the number of associated concepts.

学科与关键词

关键词
Knowledge tracingLearning processArtificial intelligence in educationLearner modeling
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
EXPERT SYSTEMS WITH APPLICATIONS
发表日期
2024-03-15
卷期
第 238 卷
页码
122280
DOI
10.1016/j.eswa.2023.122280
语言
ENGLISH
成果收录
SCIE
资助标注
National Key R&D Pro-gram of China [2022ZD0117103]; National Natural Science Foundation of China [62077021, 62293554]; Higher Education Science Research Program of China Association of Higher Education [23XXK0301]; Hubei Provincial Natural Science Foundation of China [2022CFB414, 2023AFA020]; Fundamental Research Funds for the Central Uni-versities [CCNU22LJ005]

作者

  • S

    Sun, Jianwen (第一作者)

  • W

    Wei, Mengqi

查看全部 6 位作者收起作者
  • F

    Feng, Jintian

  • Y

    Yu, Fenghua

  • L

    Li, Qing

  • Z

    Zou, Rui (通讯)

    cent china normal univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417