史湘衣,马艳

• 1:同济大学物理科学与工程学院

摘要(Abstract)：

面临高考改革分批进行，大学新生知识水平、结构差异增大，现有评价方案较少关注到对学生认知具有重要影响的知识结构，进而较难精准辨别出存在学习困难的学生。对此，本文基于学生知识掌握情况将学生在大中衔接中的类型分为衔接优良均衡型、衔接优良不均衡型、衔接一般均衡型、衔接一般不均衡型；分别使用单向、双向的Apriori算法对本科新生物理学习数据进行挖掘、生成关联规则；之后，使用基于教材的学科知识图谱对关联规则进行筛选，形成不同类型学生的个性化认知图谱。研究结果表明，学生在大中衔接过程中知识结构与学生成绩基本呈正相关，四种类型学生的知识结构有明显差异。此外，本文还基于研究结果对新高考改革背景下学生精准评价策略提供建议。

关键词(KeyWords)： 认知图谱;关联规则;知识图谱;机器学习;个性化学习

Abstract:

Keywords:

基金项目(Foundation): 2023教育部产学合作协同育人项目:改革物理实验教学,培养综合创新人才——数字全息试验仪的改装及应用(项目编号:230807116144636);; 国家自然科学基金项目:高端医药光谱成像与智能检测分析仪器研制(项目编号:62027810)

作者(Author): 史湘衣,马艳

参考文献(References)：

• [1] 国务院关于深化考试招生制度改革的实施意见(国发[2014]35 号)[OL].http://www.moe.gov.cn/jyb_xxgk/moe_1777/moe_1778/201409/t20140904_174543.html.
• [2] 钟秉林，王新凤.新高考的现实困境、理性遵循与策略选择[J].教育学报，2019,15(5):62-69.ZHONG B L,WANG X F.The real dilemmas,rational adherence,and strategic choices of the new college entrance examination[J].Journal of Education,2019,15(5):62-69.(in Chinese)
• [3] 梁德婧.高中物理与大学物理的衔接问题研究[D].苏州：苏州大学，2020:16-19.
• [4] 万海鹏，王琦，余胜泉.基于学习认知图谱的适应性学习框架构建与应用[J].现代远距离教育，2022,No.202(04):73-82.WAN H P,WANG Q,YU S Q.Construction and application of an adaptive learning framework based on learning cognitive map[J].Modern Distance Education,2022,No.202(04):73-82.(in Chinese)
• [5] CHEN Q,ZHU G,LIU Q,et al.Development of a multiple-choice problem-solving categorization test for assessment of student knowledge structure[J].Physical Review Physics Education Research,2020,16(2):020120.
• [6] CHI M,FELTOVICH P J,GLASER R.Categorization and Representation of physics problems by experts and novices[J].Cognitive Science,1981,5(2):121-152.
• [7] 张萍，涂清云，张齐齐，等.改革教学模式促进学生物理学习态度正向发展[J].中国大学教学，2014(2):5.ZHANG P,TU Q Y,ZHANG Q Q,et al.Reforming teaching methods to promote positive development of students' attitudes towards physics learning[J].Chinese University Teaching,2014(2):5.(in Chinese)
• [8] HAMMER D.Tapping epistemological resources for learning physics[J].Journal of the Learning Science,2003:53-59.
• [9] 赵国庆，李欣媛，路通，等.从认知地图到认知图谱：相似概念的跨学科审视[J].现代远程教育研究，2021,33(5):14-25.ZHAO G Q,LI X Y,LU T,et al.From cognitive maps to cognitive graphs:An interdisciplinary examination of similar concepts[J].Modern Distance Education Research,2021,33(5):14-25.(in Chinese)
• [10] 董晓晓，周东岱，顾恒年.面向学科核心素养发展的学生学科认知图谱构建研究[J].电化教育研究，2023,44(6):90-96,103.DONG X X,ZHOU D D,GU H N.Research on the construction of students' subject cognitive maps for the development of subject core literacy[J].E-education Research,2023,44(06):90-96,103.(in Chinese)
• [11] LV P,WANG X,XU J,et al.Utilizing knowledge graph and student testing behavior data for personalized exercise recommendation[C].ACM TURC '18:Proceedings of ACM Turing Celebration Conference,2018:53-59.
• [12] HAO G,ZHANG T,WANG X.Description of personalized learning characteristics in education oriented knowledge graph[M].2021 4th International Conference on Information Systems and Computer Aided Education,2021:2495-2498.
• [13] 郭鹏，蔡骋.基于聚类和关联算法的学生成绩挖掘与分析[J].计算机工程与应用，2019,55(17):169-179.GUO P,CAI C.Mining and analyzing student performance based on clustering and association algorithms[J].Computer Engineering and Applications,2019,55(17):169-179.(in Chinese)
• [14] 赵洪英，蔡乐才，李先杰.关联规则挖掘的Apriori算法综述[J].四川理工学院学报(自然科学版),2011,24(1):66-70.ZHAO H Y,CAI L C,LI X J.A review of the apriori algorithm for association rule mining[J].Journal of Sichuan University of Science & Engineering (Natural Science Edition),2011,24(1):66-70.(in Chinese)
• [15] 崔妍，包志强.关联规则挖掘综述[J].计算机应用研究，2016,33(2):330-334.CUI Y,BAO Z Q.A review of association rule mining[J].Computer Applications Research,2016,33(2):330-334.(in Chinese)
• [16] QIANG Y,HU Y.Application of improved apriori algorithm on educational information[C].Fifth International Conference on Genetic & Evolutionary Computing.IEEE,2011:330-332.
• [17] JHA J,RAGHA L.Educational data mining using improved Apriori Algorithm[J].International Journal of Information and Computation Technology,2013:411-418.
• [18] ZHAN J,FAN X,ZHAO Y.Automatic rules generation for teaching strategies improvement[C].CSAE '20:Proceedings of the 4th International Conference on Computer Science and Application Engineering.2020:1-5.
• [19] ANDREW G,JENNIFER H.Data analysis using regression and multilevel/hierarchical models,2006:529-543.
• [20] 张宁，贾自艳，史忠植.使用KNN算法的文本分类[J].计算机工程，2005(8):171-172,185.ZHANG N,JIA Z Y,SHI Z Z.Text classification using KNN algorithm[J].Computer Engineering,2005(8):171-172,185.(in Chinese)
• [21] 梁英，张海悦，张玉海，等.医学统计学试卷质量分析评价与教学策略思考[J].中国卫生统计，2023,40(4):616-618.LIANG Y,ZHANG H Y,ZHANG Y H,et al.Analysis and evaluation of the quality of medical statistics examination papers and teaching strategy reflections[J].China Health Statistics,2023,40(4):616-618.(in Chinese)
• [22] 张永爱，曹弘毅，褚静，等.护理专业考试命题与试卷分析中的问题及要点解析[J].中华护理教育，2021,18(8):723-726.ZHANG Y A,CAO H Y,CHU J,et al.Problems and Key Points Analysis in the examination and Paper analysis of nursing majors[J].Chinese Nursing Education,2021,18(8):723-726.(in Chinese)
• [23] 王惠惠，董永权，和文斌，等.基于聚类集成的学生群体画像构建[J].江苏师范大学学报(自然科学版),2022,40(3):46-50.WANG H H,DONG Y Q,HE W B,et al.Construction of student group portraits based on cluster ensemble[J].Journal of Jiangsu Normal University (Natural Science Edition),2022,40(3):46-50.(in Chinese)
• [24] 王凤肆.教育大数据：考核评价数据分析、挖掘与应用[M].北京：科学出版社，2020:61-66.
• [25] 南晓鹏.新高考生源学生学习适应性类型及其对应群体特征：以某试点省份本科高校为例[J].现代教育管理，2021,(8):18-25.NAN X P.Types of learning adaptability and corresponding group characteristics of new college entrance examination students:A case study of a pilot province's undergraduate colleges[J].Modern Education Management,2021,(8):18-25.(in Chinese)