计算机科学 ›› 2026, Vol. 53 ›› Issue (8): 9-19.doi: 10.11896/jsjkx.250600231

• 数据库 & 大数据 & 数据科学 • 上一篇    下一篇

面向学习者个性化画像的SOR标签体系构建与生成

赖英旭, 张雨薇, 庄俊玺   

  1. 北京工业大学计算机学院 北京 100124
  • 收稿日期:2025-06-30 修回日期:2025-10-13 出版日期:2026-08-15 发布日期:2026-08-17
  • 通讯作者: 庄俊玺(zhuangjunxi@bjut.edu.cn)
  • 作者简介:(laiyingxu@bjut.edu.cn)
  • 基金资助:
    北京市教育科学“十四五”规划2023年度重点课题(CGAA23034)

Construction and Generation of SOR Label System for Learner Personalized Portrait

LAI Yingxu, ZHANG Yuwei, ZHUANG Junxi   

  1. School of Computer Science, Beijing University of Technology, Beijing 100124, China
  • Received:2025-06-30 Revised:2025-10-13 Published:2026-08-15 Online:2026-08-17
  • About author:LAI Yingxu,born in 1973,Ph.D,professor,is a member of CCF(No.F3875M).Her main research interests include network security and trusted computing.
    ZHUANG Junxi,born in 1981,Ph.D,lecturer.Her main research interests include network security and trusted computing.
  • Supported by:
    Key Project of Beijing Education Science “14th Five Year Plan” for 2023(CGAA23034).

摘要: 随着在线教育和个性化教育的不断发展,如何利用海量在线学习数据构建准确、个性化的学习者画像,成为当前的研究热点。针对现有学习者画像相关研究存在忽略个体差异性、缺乏系统的理论指导等问题,提出一种面向学习者个性化画像的SOR标签体系构建与生成方法。该方法首先结合SOR理论构建个性化标签体系,提取个性化标签,挖掘学习者的个体差异性;其次,基于多标签分类模型,学习特征和个性化标签之间的复杂关系,实现对个性化标签的精准预测以及动态生成画像标签;最后,基于SOR理论构建学习者画像,揭示环境刺激、个体认知与学习行为之间的关系。实验基于公开MOOC数据集展开,通过对教学真实场景——辍学率的预测来验证本文标签体系的有效性,结果表明,所提方法的预测准确率较次优标签体系提升了0.91%,验证了所提方法在学习者个性化标签挖掘与标签体系构建方面的有效性。

关键词: 学习者画像, SOR理论, 个性化标签, 标签构建, 多标签分类

Abstract: With the development of online education and personalized education,how to utilize massive online learner data to construct accurate and personalized learner portrait has become a current research hotspot.Addressing the issues in existing learner portrait research,such as neglecting individual differences and lacking systematic theoretical guidance,a method for constructing and generating a SOR label system for learner personalized portrait is proposed.Firstly,this method combines SOR theory to construct a personalized label system,extracts personalized labels,and explores individual differences among learners.Secondly,based on a multi-label classification model,it learns the complex relationship between features and personalized labels,achieving accurate prediction of personalized labels and dynamic generation of portrait labels.Finally,it constructs learner portrait based on SOR theory,revealing the relationship between environmental stimuli,individual cognition,and learning behavior.Experiment is conducted based on a public MOOC dataset,validating the effectiveness of the proposed label system through predicting the dropout rate in real teaching scenarios,achieving a 0.91% improvement in prediction accuracy over the second-best label system.The results verify the effectiveness of this method in mining learner personalized labels and constructing label systems.

Key words: Learner portrait, SOR theory, Personalized label, Label construction, Multi label classification

中图分类号: 

  • TP391
[1] HAN X Q,YI J,ZHOU W,et al.Personalized Online Course Recommendation Model Based on Hypergraph Enhanement[J].Computer Engineering and Applications,2026,62(2):257-265.
[2] HAO X J,GU X Q.AI reshapes the concept of knowledge:Knowledge creation and educational development under the influence of data science[J].China Distance Education,2023,43(5):13-23.
[3] XU F,YING J R.Literature review of persona at home andabroad[J].Research on Library Science,2020(12):7-16.
[4] WU F,LYU F,REN J,et al.Characterizing Internet card user portraits for efficient churn prediction model design[J].IEEE Trans on Mobile Computing,2023,23(2):1735-1752.
[5] LI G,CHEN W,YAN X,et al.Modeling and analysis of group user portrait through WeChat mini program[J].Wireless Communications and Mobile Computing,2022,2022(1):2515962.
[6] SHAO Y B,QIN Y H,CUI Y J,et al.A method for generating user portraits by integrating multi-granularity information[J].Application Research of Computers,2024,41(2):401-407.
[7] FAN H D.Research on the construction method of learner digit-al portraits based on learning analytics technology[D].Harbin:Harbin Institute of Technology,2023.
[8] WANG S Q,LIU Z F,WANG J M,et al.A Review of Scholar Profiling Research[J].Library and Information Service,2022,66(20):73-81.
[9] YUAN S,TANG J,GU X T.A survey on scholar profiling techniques in the open Internet[J].Journal of Computer Research and Development,2018,55(9):1903-1919.
[10] CHEN Q,LIU R D.Contemporary Educational Psychology[M].Beijing:Beijing Normal University Press,2007.
[11] LI Z H,SHI J C,WANG Y C.The impact of AI technologyadoption on the innovation performance of researchers[J].Research in Science and Technology.2025,43(10):2056-2065.
[12] ZHAI M Y,CHENG J,WANG S T,et al.Analysis of student educational portraits based on K-prototype clustering[J].Journal of Dalian University of Technology(Social Sciences Edition),2021,42(6):22-31.
[13] ALVAREZ-GARCIA M,ARENAS-PARRA M,IBAR-ALON-SO R.Uncovering student profiles.An explainable cluster analysis approach to PISA 2022[J].Computers & Education,2024,223:105166.
[14] LING Y L,ZHANG X,LI X,et al.Application of improved k-means algorithm in student consumption portrait[J].Computer Technology and Development,2021,31(10):122-127.
[15] LIAO S T.Construction and application of blended universityEnglish learner portraits[D].Chengdu:University of Electronic Science and Technology of China,2024.
[16] ZHAO C,LI X.Research on the construction of tag models for learning portraits in online learning spaces[J].Computer Technology and Development.2023,33(10):176-182.
[17] ZHAI M Y,WANG S T,WANG Y Z,et al.An interpretable prediction method for university student academic crisis warning[J].Complex & Intelligent Systems,2022,8(1):323-336.
[18] RICO-JUAN J R,SÁNCHEZ-CARTAGENA V M,VALERO-MAS J J,et al.Identifying Student Profiles Within Online Judge Systems Using Explainable Artificial Intelligence[J].IEEE Trans on Learning Technologies,2023,16(6):955-969.
[19] TIAN Y H.Research on MOOC learning situation early warning based on learner portraits[D].Shanghai:East China Normal University,2020.
[20] HUANG S J,XU M.Research on the impact mechanism of mobile e-commerce live broadcasting on users’ online purchase intention based on SOR theory[J].Statistics and Management,2021,7(7):122-128.
[21] MA J W,ZHANG Y F,PENG L H,et al.Empirical study on user portraits of FoMO in mobile social media in the new media environment[J].Library and Information Work,2024,68(6):60-71.
[22] CHARTE F,RIVERA A J,DEL JESUS M J,et al.MLS-MOTE:Approaching imbalanced multilabel learning through synthetic instance generation[J].Knowledge-Based Systems,2015,89:385-397.
[23] VANDENHENDE S,GEORGOULIS S,VAN GANSBEKE W,et al.Multi-task learning for dense prediction tasks:A survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(7):3614-3633.
[24] VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:5998-6008.
[25] YANG M H,REN C,XIE B L,et al.Employment profiling of students based on campus behavioral characteristics[J].Library Tribune,2024,44(1):62-70.
[26] LI R.Research on behavioral label system of college English online learner profile[D].Chengdu:University of Electronic Science and Technology of China,2021.
[27] GE D,WU Y W,LIU S N Y.Research on low-cost self-evolving learner profile model[J].Computer Engineering and Applications,2023,59(11):141-150.
[28] HUANG Y M,ZHAO C C.Research on third-level short video user profiling based on improved topic modeling method[J].Computer Science,2024,51(S1):698-704.
[29] WAN J S,CHEN L,WU J H,et al.Social user profile modeling based on KD-Tree clustering[J].Computer Science,2019,46(S1):442-445,467.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!