反馈式个性化试题推荐方法
|
摘要
面向学生的试题推荐是个性化在线教育领域重要的研究课题,现有的试题推荐方法忽视了难度和认知层次的区分。通过从难度、认知层次、题型和考核的知识点对试题属性进行标准化,以及定义难度能力矩阵和认知能力矩阵来评价学生的能力,提出基于内容的试题推荐算法和基于反馈的自适应的难度调整策略。个性化的试题推荐系统框架以及应用表明,该方法能够客观评价学生的能力和试题特性,能根据学生个体差异进行推荐的同时避免教师在试题属性初始设置中的偏差。
Question recommendation for students is a significant research direction in the field of personalized online education. Unfortunately,current studies ignore the distinction between the difficulty of questions and cognitive level.Students' abilities are evaluated by standardizing question attributes from difficulty,cognitive level,question type,and assessment knowledge points,and by defining a difficulty capability matrix and a cognitive ability matrix. Therefore,we proposed a content-based question recommendation algorithm and a feedback-based adaptive difficulty adjustment strategy. The personalized recommendation system framework and applications show that the method can objectively evaluate students' abilities and characteristics of the questions. It can also make recommendations based on student individual differences while also avoiding teachers' deviations in the initial setting of the test attributes.
Question recommendation for students is a significant research direction in the field of personalized online education. Unfortunately,current studies ignore the distinction between the difficulty of questions and cognitive level.Students' abilities are evaluated by standardizing question attributes from difficulty,cognitive level,question type,and assessment knowledge points,and by defining a difficulty capability matrix and a cognitive ability matrix. Therefore,we proposed a content-based question recommendation algorithm and a feedback-based adaptive difficulty adjustment strategy. The personalized recommendation system framework and applications show that the method can objectively evaluate students' abilities and characteristics of the questions. It can also make recommendations based on student individual differences while also avoiding teachers' deviations in the initial setting of the test attributes.
引文
[1]Anshari M,Alas Y,Guan L S.Developing online learning resources:Big data,social networks,and cloud computing to support pervasive knowledge[J].Education&Information Technologies,2016,21(6):1663-1677.
[2]Dascalu M I,Bodea C N,Moldoveanu A,et al.A recommender agent based on learning styles for better virtual collaborative learning experiences[J].Computers in Human Behavior,2015,45(C):243-253.
[3]朱天宇,黄振亚,陈恩红等.基于认知诊断的个性化试题推荐方法[J].计算机学报,2017,40(1):176-191.
[4]Dwivedi P,Bharadwaj K K.E-Learning recommender system for a group of learners based on the unified learner profile approach[J].Expert Systems,2015,32(2):264-276.
[5]黄立威,江碧涛,吕守业,等.基于深度学习的推荐系统[J/OL].计算机学报,2018年在线发布.http://cjc.ict.ac.cn/online/bfpub/hlww-2018124152810.pdf.
[6]黄璐,林川杰,何军,等.融合主题模型和协同过滤的多样化移动应用推荐[J].软件学报,2017,28(3):708-720.
[7]燕彩蓉,张青龙,赵雪,等.基于广义高斯分布的贝叶斯概率矩阵分解方法[J].计算机研究与发展,2016,53(12):2793-2800.
[8]Bobadilla J,Ortega F,Hernando A.Recommender systems survey[J].Knowledge-Based Systems,2013,46(1):109-132.
[9]南志文,苏厚勤,周元军.采用代理和Ajax技术设计开发RSS个人信息聚合系统[J].计算机应用与软件,2011,28(9):140-143.
[10]皮勇泽,苏厚勤,黄琴峰.中医针灸临床治疗专家系统的研究与实现[J].计算机应用与软件,2015,32(6):99-103.
[2]Dascalu M I,Bodea C N,Moldoveanu A,et al.A recommender agent based on learning styles for better virtual collaborative learning experiences[J].Computers in Human Behavior,2015,45(C):243-253.
[3]朱天宇,黄振亚,陈恩红等.基于认知诊断的个性化试题推荐方法[J].计算机学报,2017,40(1):176-191.
[4]Dwivedi P,Bharadwaj K K.E-Learning recommender system for a group of learners based on the unified learner profile approach[J].Expert Systems,2015,32(2):264-276.
[5]黄立威,江碧涛,吕守业,等.基于深度学习的推荐系统[J/OL].计算机学报,2018年在线发布.http://cjc.ict.ac.cn/online/bfpub/hlww-2018124152810.pdf.
[6]黄璐,林川杰,何军,等.融合主题模型和协同过滤的多样化移动应用推荐[J].软件学报,2017,28(3):708-720.
[7]燕彩蓉,张青龙,赵雪,等.基于广义高斯分布的贝叶斯概率矩阵分解方法[J].计算机研究与发展,2016,53(12):2793-2800.
[8]Bobadilla J,Ortega F,Hernando A.Recommender systems survey[J].Knowledge-Based Systems,2013,46(1):109-132.
[9]南志文,苏厚勤,周元军.采用代理和Ajax技术设计开发RSS个人信息聚合系统[J].计算机应用与软件,2011,28(9):140-143.
[10]皮勇泽,苏厚勤,黄琴峰.中医针灸临床治疗专家系统的研究与实现[J].计算机应用与软件,2015,32(6):99-103.