计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (1): 21-40.DOI: 10.3778/j.issn.1673-9418.2105111

• 综述·探索 • 上一篇    下一篇

个性化学习推荐研究综述

吴正洋+(), 汤庸, 刘海   

  1. 华南师范大学 计算机学院,广州 510631
  • 收稿日期:2021-05-28 修回日期:2021-09-17 出版日期:2022-01-01 发布日期:2021-09-24
  • 通讯作者: + E-mail: wuzhengyang@m.scnu.edu.cn
  • 作者简介:吴正洋(1980—),男,河北衡水人,博士,高级工程师,硕士生导师,主要研究方向为教育人工智能、教育数据挖掘、协同教育技术等。
    汤庸(1964—),男,湖南张家界人,博士,教授, 博士生导师,主要研究方向为教育大数据、社交网络、推荐系统等。
    刘海(1974—),男,湖南张家界人,博士,副教授,硕士生导师,主要研究方向为教育数据挖掘、知识图谱、自然语言处理等。
  • 基金资助:
    国家自然科学基金广东大数据中心重点项目(U1811263)

Survey of Personalized Learning Recommendation

WU Zhengyang+(), TANG Yong, LIU Hai   

  1. School of Computer Science, South China Normal University, Guangzhou 510631, China
  • Received:2021-05-28 Revised:2021-09-17 Online:2022-01-01 Published:2021-09-24
  • About author:WU Zhengyang, born in 1980, Ph.D., associate professor, M.S. supervisor. His research interests include educational artificial intelligence, educational data mining, collaborative educational technology, etc.
    TANG Yong, born in 1964, Ph.D., professor, Ph.D. supervisor. His research interests include educational big data, social network, recommender system, etc.
    LIU Hai, born in 1974, Ph.D., associate professor, M.S. supervisor. His research interests include educational data mining, knowledge graph, natural language processing, etc.
  • Supported by:
    Key Project of Guangdong Big Data Center of National Natural Science Foundation of China(U1811263)

摘要:

个性化学习推荐是智能学习的一个研究领域,其目标是在学习平台上给特定学习者提供有效学习资源,从而提升学习积极性与学习效果。虽然现有的推荐方法已被广泛用于教学场景,但教学活动自身的科学规律,使个性化学习推荐在个性化参数设置、推荐目标设定、评价标准设计等方面具有一定的特殊性。针对上述问题,在调研大量文献的基础上对近年来个性化学习推荐的研究进行了综述。从学习推荐通用框架、学习者建模、学习推荐对象建模、学习推荐算法、学习推荐评价五方面对个性化学习推荐的相关研究进行了系统的梳理和解读。首先提出了学习推荐系统的通用框架,其次介绍了学习者建模的思路和方法,接着讨论了学习推荐对象建模的思路和方法,然后归纳了学习推荐的算法与模型,接下来总结了学习推荐评价的设计与方法。并对这五方面现有研究的主要思想、实施方案、优势及不足进行了分析。最后还展望了个性化学习推荐未来的发展方向,为智能学习的进一步深入研究奠定了基础。

关键词: 学习者模型, 推荐算法, 知识追踪, 图神经网络, 异质信息网络

Abstract:

Personalized learning recommendation is a research field of intelligent learning. Its goal is to provide specific learners with effective learning resources on the learning platform, thereby enhancing learning enthusiasm and learning effect. Although the existing recommendation methods have been widely used in learning scenarios, the scientific rules of learning activities make personalized learning recommendations unique in terms of personalized parameter setting, recommendation goal setting, and evaluation standard design. In response to the above-mentioned problems, the research of personalized learning recommendation in recent years is reviewed on the basis of investigating a large number of literatures. The research on personalized learning recommendation is systematically sorted out and interpreted from five aspects, i.e., the general framework of learning recommendation, learner modeling, learning recommendation object modeling, learning recommendation algorithm, and learning recommendation evaluation. Firstly, the general framework of learning recommendation system is proposed. Secondly, the ideas and methods of learner modeling are introduced. Next, the ideas and methods of learning recommendation object modeling are discussed. Then, this paper summarizes the algorithm and model of learning recommendation. The following, this paper summarizes the design and method of learning recommendation evaluation. This paper also analyzes the main ideas, implementation plans, advantages and disadvantages of the existing research in these five aspects. Finally, this paper also looks forward to the future development direction of personalized learning recommendation, which lays foundation for further in-depth research on intelligent learning.

Key words: learner model, recommendation algorithm, knowledge tracking, graph neural network, heterogeneous information network

中图分类号: