基于二部图的学习资源混合推荐方法研究
|
摘要
在线学习过程中,学习者经常面临"资源过载"和"学习迷航"问题。为了解决上述问题,研究人员将信息推荐技术引入在线学习中,试图为学习者提供个性化的学习服务。近年来,协同过滤推荐方法受到广泛关注,并在实际应用中取得了较为理想的效果。然而,该方法推荐范围有限且忽视小众资源,无法满足部分学习者的个性化需求。鉴于此,文章将物理学中的热传导和物质扩散理论引入推荐系统中,建立基于二部图的学习资源混合推荐模型。该模型将基于热传导的推荐方法和基于物质扩散的推荐方法混合使用,通过引入一个可调参数,使两种方法在不同应用场景下发挥不同的作用。该模型为进一步研究个性化学习资源推荐方法提供重要参考。
Learners often encounter some problems in online learning, such as "resource overload" and "learning loses". In order to solve the above problems, information recommendation technology has been introduced into online learning, so as to provide learners with personalized learning services. In recent years, the collaborative filtering recommendation method has received wide attention and achieved satisfactory results in practical application. However, by using this method, the range of recommendations is limited and niche resources are ignored, which cannot meet learners' individual needs. Therefore, this paper introduces the theory of heat conduction and material diffusion in physics into recommendation system, and establishes a mixed recommendation model of learning resources based on bipartite network.The model will use recommendation methods based on both heat conduction and material diffusion, and the two methods can play different roles in different application scenarios according to an adjustable parameter. This model provides an important reference for further research on resource recommendation of personalized learning.
Learners often encounter some problems in online learning, such as "resource overload" and "learning loses". In order to solve the above problems, information recommendation technology has been introduced into online learning, so as to provide learners with personalized learning services. In recent years, the collaborative filtering recommendation method has received wide attention and achieved satisfactory results in practical application. However, by using this method, the range of recommendations is limited and niche resources are ignored, which cannot meet learners' individual needs. Therefore, this paper introduces the theory of heat conduction and material diffusion in physics into recommendation system, and establishes a mixed recommendation model of learning resources based on bipartite network.The model will use recommendation methods based on both heat conduction and material diffusion, and the two methods can play different roles in different application scenarios according to an adjustable parameter. This model provides an important reference for further research on resource recommendation of personalized learning.
引文
[1]MOOC completion rates:the data[EB/OL].[2015-06-01].http://www.katyjordan.com/MOOC-project.html.
[2]赵蔚,姜强,王朋娇,等.本体驱动的e-Learning知识资源个性化推荐研究[J].中国电化教育,2015(5):84-89.
[3]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(1):69-76.
[4]陈敏,余胜泉.泛在学习环境下感知学习过程情境的推荐系统设计[J].电化教育研究,2015(4):76-82,89.
[5]王剑,陈涛.个性化e-Learning协作学习推荐系统研究[J].中国远程教育,2016(7):44-51,76.
[6]刘迎春,孙家宝.基于Qo S偏好相似度的网络教育服务推荐研究[J].电化教育研究,2013(6):34-39.
[7]刘小雪.基于Web使用挖掘的e-Learning自适应推荐系统[J].电化教育研究,2012(4):82-84.
[8]白雪,赵蔚,姜强,等.基于标签的教育资源管理与推荐模型构建——来自社会化标注网站的启示[J].现代教育技术,2014,24(5):96-102.
[9]黄志芳,赵呈领,黄祥玉,等.基于情境感知的适应性学习路径推荐研究[J].电化教育研究,2015(5):77-84.
[10]吴笛,李保强.基于情境感知的学习资源关联分析与推荐模型研究[J].中国远程教育,2017(2):59-65.
[11]徐天伟,宋雅婷,段崇江.基于协同过滤的个性化推荐选课系统研究[J].现代教育技术,2014,24(6):92-98.
[12]孙歆,王永固,邱飞岳.基于协同过滤技术的在线学习资源个性化推荐系统研究[J].中国远程教育,2012(8):78-82.
[13]李保强,吴笛.基于知识关联的学习资源混合协同过滤推荐研究[J].电化教育研究,2016(6):77-83.
[14]杨丽娜,魏永红.情境化的泛在学习资源智能推荐研究[J].电化教育研究,2014(10):103-109.
[15]余平,管珏琪,徐显龙.情境信息及其在智慧学习资源推荐中的应用研究[J].电化教育研究,2016(2):54-61.
[16]丁永刚,张馨,桑秋侠,等.融合学习者社交网络的协同过滤学习资源推荐[J].现代教育技术,2016,26(2):108-114.
[17]吴正洋,汤庸,黄昌勤,等.社交网络下学习推荐研究与实践[J].中国电化教育,2016(3):75-81,98.
[18]赵铮,李振,周东岱,等.智慧学习空间中学习行为分析及推荐系统研究[J].现代教育技术,2016,26(1):100-106.
[2]赵蔚,姜强,王朋娇,等.本体驱动的e-Learning知识资源个性化推荐研究[J].中国电化教育,2015(5):84-89.
[3]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(1):69-76.
[4]陈敏,余胜泉.泛在学习环境下感知学习过程情境的推荐系统设计[J].电化教育研究,2015(4):76-82,89.
[5]王剑,陈涛.个性化e-Learning协作学习推荐系统研究[J].中国远程教育,2016(7):44-51,76.
[6]刘迎春,孙家宝.基于Qo S偏好相似度的网络教育服务推荐研究[J].电化教育研究,2013(6):34-39.
[7]刘小雪.基于Web使用挖掘的e-Learning自适应推荐系统[J].电化教育研究,2012(4):82-84.
[8]白雪,赵蔚,姜强,等.基于标签的教育资源管理与推荐模型构建——来自社会化标注网站的启示[J].现代教育技术,2014,24(5):96-102.
[9]黄志芳,赵呈领,黄祥玉,等.基于情境感知的适应性学习路径推荐研究[J].电化教育研究,2015(5):77-84.
[10]吴笛,李保强.基于情境感知的学习资源关联分析与推荐模型研究[J].中国远程教育,2017(2):59-65.
[11]徐天伟,宋雅婷,段崇江.基于协同过滤的个性化推荐选课系统研究[J].现代教育技术,2014,24(6):92-98.
[12]孙歆,王永固,邱飞岳.基于协同过滤技术的在线学习资源个性化推荐系统研究[J].中国远程教育,2012(8):78-82.
[13]李保强,吴笛.基于知识关联的学习资源混合协同过滤推荐研究[J].电化教育研究,2016(6):77-83.
[14]杨丽娜,魏永红.情境化的泛在学习资源智能推荐研究[J].电化教育研究,2014(10):103-109.
[15]余平,管珏琪,徐显龙.情境信息及其在智慧学习资源推荐中的应用研究[J].电化教育研究,2016(2):54-61.
[16]丁永刚,张馨,桑秋侠,等.融合学习者社交网络的协同过滤学习资源推荐[J].现代教育技术,2016,26(2):108-114.
[17]吴正洋,汤庸,黄昌勤,等.社交网络下学习推荐研究与实践[J].中国电化教育,2016(3):75-81,98.
[18]赵铮,李振,周东岱,等.智慧学习空间中学习行为分析及推荐系统研究[J].现代教育技术,2016,26(1):100-106.