概念图能够直观地展示概念间的相互关系,为教师提供概念相关性的建议,因而成为教师进行个性化教学的重要工具。然而,如何生成能反映学生学习能力并有效指导教师教学的概念图是目前概念图研究一大难题。该文提出了一种新的自动概念图生成模型C-IK2。C-IK2模型考虑学生的不同学习特点和不同概念理解程度,通过Birch算法对学生概念掌握程度特征进行聚类处理得到学生分簇。同时该模型考虑概念图具有层次结构,针对传统LPG算法在处理层次结构方面的不足进行了改进。通过融合改进的LPG算法,同时改进K2算法的有效输入序列,最终生成具有不同学生学习特征的层次结构概念图。该文使用两个标准数据集进行实验,与现有基于序列的最新改进K2算法进行对比,C-IK2模型在图准确度上提高了7.7%。与现有基于评分的贝叶斯网络结构学习方法相比,C-IK2模型的图结构质量提高了3.1%。结果表明,C-IK2模型能有效区分学生对概念的理解程度,生成反映理解程度的层次结构概念图,从而帮助教师进行针对性地个性化教学。
Abstract
Concept maps can intuitively display the correlation between concepts and provide teachers with teaching suggestions. Therefore, concept maps have become an important tool for teachers to conduct personalized teaching. However, how to generate a concept map that can reflect students’ learning ability and effectively guide teachers’ teaching is a big challenge in the current concept map research. This paper proposes a new automatic concept map generation model C-IK2. The C-IK2 model considers students’ different learning characteristics and concept understanding levels, and uses Birch algorithm to cluster students’ concept mastery characteristics to obtain student clusters. At the same time, the model considers the hierarchical structure of the concept map and is used to guide teachers’ teaching, combined with the lack of hierarchical structure of the improved LPG algorithm and the effective input sequence of the improved K2 algorithm to generate hierarchical conceptual maps with different learning characteristics of students. The experiment is based on ASIA standard data, and compared with the existing sequence-based latest improved K2 algorithm, the C-IK2 model improves the accuracy of the graph by 7.7%. Compared with existing score-based Bayesian network structure learning methods, the graph structure quality of the C-IK2 model is improved by 3.1%. Experiments show that the C-IK2 model effectively distinguishes different students’ understanding of concepts, and the hierarchical conceptual map generated at the same time has certain effectiveness, thereby helping teachers to carry out personalized teaching.
关键词
LPG算法 /
K2算法 /
概念图 /
C-IK2 模型
{{custom_keyword}} /
Key words
LPG algorithm /
K2 algorithm /
concept map /
C-IK2 model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] GUDIVADA V N. Cognitive analytics driven personalized learning[J]. Educational Technology, 2017: 23-31.
[2] ZHOU Y, HUANG C, HU Q, et al. Personalized learning full-path recommendation model based on LSTM neural networks[J]. Information Sciences, 2018, 444: 135-152.
[3] SALINAS J, DE BENITO B. Construction of Personalized Learning Pathways through Mixed Methods[J].Comunicar: Media Education Research Journal, 2020, 28(65): 31-41.
[4] MING Q, LI R. Analysis and design of personalized learning system based on decision tree technology[C]//Proceedings of the International Conference on Machine Learning and Big Data Analytics for IoT Security and Privacy, Springer International Publishing, 2021: 119-126.
[5] XIE H, ZOU D, ZHANG R, et al. Personalized word learning for university students: A profile-based method for e-learning systems[J]. Journal of Computing in Higher Education, 2019, 31: 273-289.
[6] MARKHAM K M,MINTZES J J, JONES M G. The concept map as a research and evaluation tool: Further evidence of validity[J]. Journal of Research in Science Teaching, 1994, 31(1): 91-101.
[7] ATAPATTU T, FALKNER K, FALKNER N. A comprehensive text analysis of lecture slides to generate concept maps[J]. Computers & Education, 2017, 115: 96-113.
[8] HUANG X, YANG K, LAWRENCE V B. An efficient data mining approach to concept map generation for adaptive learning[C]//Proceedings of the Industrial Conference, Hamburg, Germany, Springer International Publishing, 2015: 247-260.
[9] SHAO Z, LI Y, WANG X, et al. Research on a new automatic generation algorithm of concept map based on text analysis and association rules mining[J]. Journal of Ambient Intelligence and Humanized Computing, 2020, 11: 539-551.
[10] ALFONSO D,MANJARRS A, PICKIN S. Semi-automatic generation of competency maps based on educational data mining[J]. International Journal of Computational Intelligence Systems, 2019, 12(2): 744.
[11] COOPER G F. E. Herskovits a bayesian method for the induction of probabilistic networks from data[J]. Machine Learning, 1992, 9(4): 309-347.
[12] TABAR V R, ESKANDARI F, SALIMI S, et al. Finding a set of candidate parents using dependency criterion for the K2 algorithm[J]. Pattern Recognition Letters, 2018, 111: 23-29.
[13] LI Y, SHAO Z, WANG X, et al. A concept map-based learning paths automatic generation algorithm for adaptive learning systems[J]. IEEE Access, 2018, 7: 245-255.
[14] CHEN N S, WEI C W, CHEN H J. Mining e-Learning domain concept map from academic articles[J]. Computers & Education, 2008, 50(3): 1009-1021.
[15] WANG S,ORORBIA A, WU Z, et al. Using prerequisites to extract concept maps fromtextbooks[C]//Proceedings of the 25th Acm International on Conference on Information and Knowledge Management. 2016: 317-326.
[16] 盛泳潘,付雪峰,吴天星.基于开放域抽取的多文档概念图构建研究[J].计算机应用研究,2020,37(01):19-25.
[17] TSENG S S, SUE P C, SU J M, et al. A new approach for constructing the concept map[J]. Computers & Education, 2007, 49(3): 691-707.
[18] ROMERO M C, CAZORLA M, BUZN GARCA O. Meaningful learning using concept maps as a learning strategy[J]. Journal of Technology and Science Education, 2017,7(3): 313-332.
[19] SCANAGATTA M, SALMERN A, STELLA F. A survey on Bayesian network structure learning from data[J]. Progress in Artificial Intelligence, 2019, 8: 425-439.
[20] LIAO Z A, SHARMA C,CUSSENS J, et al. Finding all Bayesian network structures within a factor of optimal[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 33(01): 7892-7899.
[21] GMEZ J A, MATEO J L, PUERTA J M. Learning Bayesian networks by hill climbing: efficient methods based on progressive restriction of the neighborhood[J]. Data Mining and Knowledge Discovery, 2011, 22: 106-148.
[22] TRABELSI G,LERAY P, BEN AYED M, et al. Dynamic MMHC: A local search algorithm for dynamic Bayesian network structure learning[C]//Proceedings of the 12th International Symposium, Springer Berlin Heidelberg, 2013: 392-403.
[23] COOPER G F, HERSKOVITS E. A Bayesian method for the induction of probabilistic networks from data[J]. Machine Learning, 1992, 9: 309-347.
[24] 徐苗,王慧玲,梁义,綦小龙.基于K2算法的因果结构学习研究综述[J].伊犁师范学院学报(自然科学版),2021,15(01):51-57.
[25] AOUAY S, JAMOUSSI S, AYED Y B. Particle swarm optimization based method for Bayesian network structure learning[C]//Proceedings of the 5th International Conference on Modeling, Simulation and Applied Optimization. IEEE, 2013: 1-6.
[26] CHEN X W, ANANTHA G, LIN X. Improving Bayesian network structure learning with mutual information-based node ordering in the K2 algorithm[J]. IEEE Transactions on Knowledge and Data Engineering, 2008, 20(5): 628-640.
[27] KO S, KIM D W. An efficient node ordering method using the conditional frequency for the K2 algorithm[J]. Pattern Recognition Letters, 2014, 40: 80-87.
[28] AI X. Node importance ranking of complex networks with entropy variation[J]. Entropy, 2017, 19(7): 303.
[29] 刘艳杰,李霞.基于贝叶斯网络的学生成绩预测[J].山东理工大学学报(自然科学版),2019,33(05):75-78.
[30] CHIANG Y J, GOODRICH M T, GROVE E F, et al. External-memory graph algorithms[C]//Proceedings of the 6th Annual ACM-SIAM Symposium on Discrete Algorithms,1995:139-149.
[31] BEHJATI S, BEIGY H. Improved K2 algorithm for Bayesian network structure learning[J]. Engineering Applications of Artificial Intelligence, 2020, 91: 103617.
[32] 黄云,郝元涛.应用R软件bnlearn程序包学习贝叶斯网络[J].中国卫生统计,2020,37(05):787-791.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家社会科学基金(AGA200016)
{{custom_fund}}
PDF(2826 KB)
