基于场景感知的学习者建模研究
|
摘要
"互联网+教育"时代,以往传统的学习场景正不断被重构,新型的学习场景逐渐向动态化、多元化、碎片化的模式发展,使得基于场景挖掘的新型个性化学习服务模式的重要性越发凸显。而学习者模型作为个性化学习服务系统的核心部件,目前还无法满足新时代下高精准的个性化服务要求。基于此,文章提出一种基于场景感知的学习者建模方法,该方法是基于近些年有关学习者特征分析模型研究的分析结果,融合学习者的场景特性,设计了一个6维度学习者特征分析模型,在此基础上,融合场景感知建模方法和频繁序列挖掘算法,计算不同学习场景下各维度学习者特征值,由此构建一个具有场景特性的个性化学习者模型,并基于该模型探讨了个性化学习服务推荐演化框架。
In the era of "Internet + education", as traditional learning scenes are constantly being reconstructed, the new learning scenes are gradually developing into dynamic, diversified and fragmented models, which makes new personalized learning service models based on scene mining more and more important. However, the learner model, as the core component of the personalized learning service system,cannot meet the high-precision personalized service requirements in the new era. Therefore, this paper proposes a learner modeling method based on context awareness. On the basis of the analysis results of recent studies on learner feature analysis models, together with the scene features of learners, a 6-dimensional learner feature analysis model is designed. Then, the context-awareness modeling method and frequent sequence mining algorithm are used to calculate the value of learner feature in each dimension under different learning scenes, and a personalized learner model with scene features is constructed.Finally, based on that model, the evolution framework of personalized learning service recommendation is discussed.
In the era of "Internet + education", as traditional learning scenes are constantly being reconstructed, the new learning scenes are gradually developing into dynamic, diversified and fragmented models, which makes new personalized learning service models based on scene mining more and more important. However, the learner model, as the core component of the personalized learning service system,cannot meet the high-precision personalized service requirements in the new era. Therefore, this paper proposes a learner modeling method based on context awareness. On the basis of the analysis results of recent studies on learner feature analysis models, together with the scene features of learners, a 6-dimensional learner feature analysis model is designed. Then, the context-awareness modeling method and frequent sequence mining algorithm are used to calculate the value of learner feature in each dimension under different learning scenes, and a personalized learner model with scene features is constructed.Finally, based on that model, the evolution framework of personalized learning service recommendation is discussed.
引文
[1]陈丽,郭玉娟,王怀波,郑勤华.新时代信息化进程中教育研究问题域框架[J].现代远程教育研究,2018(1):40-46,87.
[2]武法提,黄石华,殷宝媛.场景化:学习服务设计的新思路[J].电化教育研究,2018(12):63-69.
[3] IEEE Learning Technology Standards Committee(LTSC)[EB/OL].[2018-12-01]. http://ltsc.ieee.org/.
[4] IMS learner information package summary of changes version 1.0.1 final specification[EB/OL].[2005-01-04].https://www.imsglobal.org/profiles/lipv1p0p1/imslip_sumcv1p0p1.html.
[5]祝智庭.网络教育技术标准研究[J].电化教育研究,2001(8):72-78.
[6] BRUSILOVSKY P, MILL譧N E.User models for adaptive hypermedia and adaptive educational systems[J].The adaptive web,lecture notes in computer science,2007(4321):3-53.
[7]王晓琳,高丹丹,张际平.智能授导系统中的学习者本体构建[J].电化教育研究,2009(4):56-58,77.
[8]陈仕品,张剑平.适应性学习支持系统的学生模型研究[J].中国电化教育,2010(5):112-117.
[9]王怡涵.能力导向终身学习个性化推荐系统学习者模型构建[D].长春:东北师范大学,2011.
[10] CHRYSAFIADI K, VIRVOU M. Student modelling approaches:a literature reviewfor last decade[J].Expert system with applications,2013(40):4715-4729.
[11]黄焕.面向e-Learning的学习者情感建模及应用研究[D].武汉:华中师范大学,2014.
[12]牟智佳,武法提.电子书包中基于学习者模型的个性化学习资源推荐研究[J].电化教育研究,2015,36(1):69-76.
[13] JELENA N, ANDRINA G, VLADO G. Anatomy of student models in adaptive learning systems:a systematic literature review of individual difeferences from 2001 to 2013[J].Educational computing research, 2015, 51(4):459-489.
[14] TADLAOUI M A, AAMOU S, KHALDI M, CARVALHO R N. Learner modeling in adaptive educational systems:a comparative study[J].Modern education and computer science, 2016, 8(3):1-10.
[15]岳俊芳,陈逸.基于大数据分析的远程学习者建模与个性化学习应用[J].中国远程教育,2017(7):34-39.
[16]孙力,张婷.网络教育中个性化学习者模型的设计与分析[J].远程教育杂志,2017,35(3):93-101.
[17]孙海民.个性特征对网络学习行为影响研究的关键问题探究[J].电化教育研究,2012,33(10):50-55,63.
[18]哈维·席尔瓦.多元智能新视点丛书:多元智能与学习风格[M].张玲,译.北京:教育科学出版社,2003:146.
[19] ACHAR A, LAXMAN S, SASTRY P S. A unified view of the apriori-based algorithms for frequent episode discovery[J]. Knowledge&information systems, 2012, 31(2):223-250.
[20] BIRANT D, KUT A.ST-DBSCAN:an algorithm for clustering spatial-temporal data[J]. Data&knowledge engineering, 2007, 60(1):208-221.
[2]武法提,黄石华,殷宝媛.场景化:学习服务设计的新思路[J].电化教育研究,2018(12):63-69.
[3] IEEE Learning Technology Standards Committee(LTSC)[EB/OL].[2018-12-01]. http://ltsc.ieee.org/.
[4] IMS learner information package summary of changes version 1.0.1 final specification[EB/OL].[2005-01-04].https://www.imsglobal.org/profiles/lipv1p0p1/imslip_sumcv1p0p1.html.
[5]祝智庭.网络教育技术标准研究[J].电化教育研究,2001(8):72-78.
[6] BRUSILOVSKY P, MILL譧N E.User models for adaptive hypermedia and adaptive educational systems[J].The adaptive web,lecture notes in computer science,2007(4321):3-53.
[7]王晓琳,高丹丹,张际平.智能授导系统中的学习者本体构建[J].电化教育研究,2009(4):56-58,77.
[8]陈仕品,张剑平.适应性学习支持系统的学生模型研究[J].中国电化教育,2010(5):112-117.
[9]王怡涵.能力导向终身学习个性化推荐系统学习者模型构建[D].长春:东北师范大学,2011.
[10] CHRYSAFIADI K, VIRVOU M. Student modelling approaches:a literature reviewfor last decade[J].Expert system with applications,2013(40):4715-4729.
[11]黄焕.面向e-Learning的学习者情感建模及应用研究[D].武汉:华中师范大学,2014.
[12]牟智佳,武法提.电子书包中基于学习者模型的个性化学习资源推荐研究[J].电化教育研究,2015,36(1):69-76.
[13] JELENA N, ANDRINA G, VLADO G. Anatomy of student models in adaptive learning systems:a systematic literature review of individual difeferences from 2001 to 2013[J].Educational computing research, 2015, 51(4):459-489.
[14] TADLAOUI M A, AAMOU S, KHALDI M, CARVALHO R N. Learner modeling in adaptive educational systems:a comparative study[J].Modern education and computer science, 2016, 8(3):1-10.
[15]岳俊芳,陈逸.基于大数据分析的远程学习者建模与个性化学习应用[J].中国远程教育,2017(7):34-39.
[16]孙力,张婷.网络教育中个性化学习者模型的设计与分析[J].远程教育杂志,2017,35(3):93-101.
[17]孙海民.个性特征对网络学习行为影响研究的关键问题探究[J].电化教育研究,2012,33(10):50-55,63.
[18]哈维·席尔瓦.多元智能新视点丛书:多元智能与学习风格[M].张玲,译.北京:教育科学出版社,2003:146.
[19] ACHAR A, LAXMAN S, SASTRY P S. A unified view of the apriori-based algorithms for frequent episode discovery[J]. Knowledge&information systems, 2012, 31(2):223-250.
[20] BIRANT D, KUT A.ST-DBSCAN:an algorithm for clustering spatial-temporal data[J]. Data&knowledge engineering, 2007, 60(1):208-221.