| 54 | 0 | 27 |
| 下载次数 | 被引频次 | 阅读次数 |
当前传统在线教育平台“一刀切”的教育模式不能满足在线学习者差异化的需求,因此需要一个高效、精准的个性化教育模式帮助在线学习者提高在线学习质量。本文基于多维度学习者画像赋能在线教育个性化学习路径,通过挖掘在线学习平台学生行为轨迹数据,分析在线学习者潜藏的个性化学习特征,并建立决策树分类模型开展学习群体分类,从而实现为不同类别的在线学习者提供群体智慧建议与个性化学习规划。利用真实在线学生学习数据集进行方法验证,实验结果表明该方法“特征挖掘-画像构建-路径生成-应用反馈-特征更新”的逻辑闭环可行,可直接为开放教育平台的个性化学习路径推荐提供技术支撑。
Abstract:The current “one-size-fits-all” education model of traditional online education platforms cannot meet the differentiated needs of online learners. Therefore,an efficient and precise personalized education model is needed to help online learners improve the quality of online learning. This paper empower personalized learning paths in online education based on multi-dimensional learner profiling by mining the behavioral trajectory data of students on online learning platforms,which can analyze the latent personalized learning characteristics of online learners and establish a decision tree classification model to classify learning groups,and provide collective wisdom suggestions and personalized learning plans for different types of online learners. The method proposed in this paper was verified using a real online student learning dataset. The experimental results show that the logical closed loop of“feature mining-portrait construction-path generation-application feedback-feature update ” of this method is feasible and can directly provide technical support for the personalized learning path recommendation of the open education platform.
[1]王剑,佘政.考虑多维偏好与知识结构的多目标学习路径优化[J].现代教育技术,2025,35(09):115-125.
[2]赵晶莹,吴坚.美国K-12教育领域人工智能赋能个性化学习的实践路径[J].比较教育学报,2025(5):153-166.
[3]郑雅倩,李新,李艳燕,等.人工智能视域下个性化学习路径推荐:机理、演进、价值与趋势[J].现代远距离教育,2023(03):39-47.
[4]苗煜飞,张霄宏.决策树C4. 5算法的优化与应用[J].计算机工程与应用,2015,51(13):255-258+270.
[5]李洁,朱洪亮,陈玉玲,等.基于哈希存储与事务加权的并行Apriori改进算法[J].计算机工程,2020,46(11):109-116.
[6]王小根,吕佳琳.从学习者模型到学习者孪生体——学习者建模研究综述[J].远程教育杂志,2021,39(2):53-62.
[7]Manso-Vazquez M,Caeiro-Rodriguez M,Llamas-Nistal M. An x API Application Profile to Monitor Self-Regulated Learning Strategies[J]. IEEE ACCESS,2018(6):42467-42481.
[8]赖英旭,张雨薇,庄俊玺.面向学习者个性化画像的SOR标签体系构建与生成[J].计算机科学,2025(10):1-14.
[9]ALVAREZ-GARCIA M,ARENAS-PARRA M,IBARALONSO R. Uncovering student profiles. An explainable cluster analysis approach to PISA 2022[J]. Computers&Education,2024,223:105166.
[10]赵春,李欣.网络学习空间中学习画像的标签模型构建研究[J/OL].计算机技术与发展,2023,33(10):176-182.
[11]中共中央、国务院.教育强国建设规划纲要(2024-2035年)[EB/OL].(2025-01-19)[2025-02-21]. https://www. gov. cn/zhengce/202501/content_6999913. htm.
[12]中华人民共和国教育部.2025年全国教育工作会议召开[EB/OL].(2025-01-09)[2025-02-21]. http//www. moe. gov. cn/jyb_xwfb/gzdt_gzdt/moe_1485/202501/t20250109_1174966. html.
[13]SHI D,WANG T,XING H,et al. A learning path recommendation model based on a multidimensional knowledge graph framework for e-learning[J]. Knowledge-Based Systems,2020,195(5):105618.
[14]李建伟,武佳惠,姬艳丽.面向自适应学习的个性化学习路径推荐[J].现代教育术,2023,33(01):108-117.
[15]Ntayoad W,Becker T,Temdee P. Social context-aware recommendation for personalized online learning[J].Wireless Personal Communications,2017,97(1):163-179.
[16]孔维梁,韩淑云,张昭理.人工智能支持下自适应学习路径构建[J].现代远程教育研究,2020,32(3):94-102.
[17]倪小虹,孙应飞.融合多数据源的非平稳动态贝叶斯网络学习算法[J].小型微型计算机系统,2014,35(02):374-378.
基本信息:
中图分类号:G434
引用信息:
[1]韩晶晶,王芬,陈曦.在线学习者画像驱动的个性化学习路径推荐:方法构建与实验分析[J].陕西开放大学学报,2026,28(02):21-30.
基金信息:
江苏高校哲学社会科学一般项目“基于学习轨迹数据挖掘的个性化学习路径推荐算法研究”(项目编号:2023SJYB0778); 江苏省教育科学规划课题“云环境下基于机器学习的在线教育学习者画像与个性化学习推荐算法”青年专项(项目编号:C/2023/01/118); 江苏开放大学(江苏城市职业学院)校级课题“云计算环境下基于学习轨迹数据挖掘的远程教育学习预警模型研究”(项目编号:2022XK004)
2026-06-15
2026-06-15