|
|
A Concept Interaction-Based Cognitive Diagnosis Deep Model |
ZHANG Suojuan1,2, YU Xiaohan1, CHEN Enhong2, SHEN Shuanghong2, ZHENG Yu1, HUANG Song1 |
1. College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007; 2. Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027 |
|
|
Abstract Cognitive diagnosis is an intelligent assessment technique of mining learners' cognitive state based on learning data. Concepts in learning tasks are regarded as equally important by most cognitive diagnosis deep model. Without the consideration of the interaction between concepts, diagnosis accuracy is affected and interpretability is insufficient. To solve the problems, a concept interaction-based cognitive diagnosis deep model is proposed to realize the unified representation of students' cognitive state and concept weights. In the meanwhile, an algorithm of ideal response calculation based on the Choquet integral is implemented. Finally, a deep neural network based on fuzzy measures is proposed to predict learners' response performance. Experiments show that the proposed model holds advantages in prediction results and the explanation at the concept interaction level provided for prediction results.
|
Received: 07 November 2022
|
|
Fund:National Natural Science Foundation of China(No.62207031,U20A20229) |
Corresponding Authors:
HUANG Song, Ph.D., professor. His research interests include software testing and data mining.
|
About author:: ZHANG Suojuan, Ph.D., associate professor.Her research interests include educational data mining and cognitive diagnosis. YU Xiaohan, Ph.D., associate professor. His research interests include artificial intelligence.CHEN Enhong, Ph.D., professor. His research interests include machine learning, data mining, education big data analysis and personalized recommendation system.SHEN Shuanghong, Ph.D. candidate. His research interests include data mining, student modeling and knowledge tracing.ZHENG Yu, master, teaching assistant. Her research interests include information retrieval and natural language processing. |
|
|
|
[1] 罗照盛. 认知诊断评价理论基础.北京:北京师范大学出版社,2019. (LUO Z S.Fundamentals of Cognitive Diagnostic Assessment. Beijing, China: Beijing Normal University Press, 2019.) [2] CHEN S, JOACHIMS T.Predicting Matchups and Preferences in Con-text // Proc of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2016: 775-784. [3] 涂冬波,蔡艳,高旭亮,等.高级认知诊断.北京:北京师范大学出版社, 2019. (TU D B, CAI Y, GAO X L, et al.Advanced Cognitive Diagnosis. Beijing, China: Beijing Normal University Press, 2019.) [4] EMBRETSON S E, REISE S P. Item Response Theory.Hove, UK: Psychology Press, 2000. [5] DE LA TORRE J. DINA Model and Parameter Estimation: A Didactic. Journal of Educational and Behavioral Statistics, 2009, 34(1): 115-130. [6] RECKASE M D.The Past and Future of Multidimensional Item Response Theory. Applied Psychological Measurement, 1997, 21(1): 25-36. [7] DE LA TORRE J. The Generalized DINA Model Framework. Psychometrika, 2011, 76(2): 179-199. [8] LIU Q.Towards a New Generation of Cognitive Diagnosis // Proc of the 13th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2021: 4961-4964. [9] LIU Q, WU R Z, CHEN E H, et al. Fuzzy Cognitive Diagnosis for Modelling Examinee Performance. ACM Transactions on Intelligent Systems and Technology, 2018, 9(4). DOI: 10.1145/3168361. [10] WANG F, LIU Q, CHEN E H, et al. Neural Cognitive Diagnosis for Intelligent Education Systems. Proceedings of the AAAI Confe-rence on Artificial Intelligence, 2020, 34(4): 6153-6161. [11] YANG H W, QI T L, LI J, et al. A Novel Quantitative Relationship Neural Network for Explainable Cognitive Diagnosis Model. Knowledge-Based Systems, 2022, 250. DOI: 10.1016/j.knosys.2022.109156. [12] 钟卓,唐烨伟,钟绍春,等.人工智能支持下教育知识图谱模型构建研究.电化教育研究, 2020, 41(4): 62-70. (ZHONG Z, TANG Y W, ZHONG S C, et al. Research on Constructing Model of Educational Knowledge Map Supported by Artificial Intelligence. e-Education Research, 2020, 41(4): 62-70. ) [13] PIAGET J.The Equilibration of Cognitive Structures: The Central Problem of Intellectual Development. BROWN T, THAMPY K J, trans. Chicago, USA: University of Chicago Press, 1985. [14] GAO W B, LIU Q, HUANG Z Y, et al. RCD: Relation Map Dri-ven Cognitive Diagnosis for Intelligent Education Systems // Proc of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2021: 501-510. [15] GAO L N, ZHAO Z Y, LI C, et al. Deep Cognitive Diagnosis Model for Predicting Students' Performance. Future Generation Computer Systems, 2022, 126: 252-262. [16] MENG L L, ZHANG M X, ZHANG W X, et al. CS-BKT: Introducing Item Relationship to the Bayesian Knowledge Tracing Mo-del. Interactive Learning Environments, 2019, 29(8): 1393-1403. [17] LEIGHTON J P, GIERL M J, HUNKA S M.The Attribute Hierarchy Method for Cognitive Assessment: A Variation on Tatsuoka's Rule-Space Approach. Journal of Educational Measurement, 2004, 41(3): 205-237. [18] GIERL M J, LEIGHTON J P, HUNKA S M.Using the Attribute Hierarchy Method to Make Diagnostic Inferences About Examinees' Cognitive Skills // LEIGHTON J, GIERL M, eds. Cognitive Diagnostic Assessment for Education: Theory and Applications. Cambridge, USA: Cambridge University Press, 2007: 242-274. [19] YANG Y M, LIU H X, CARBONELL J, et al. Concept Graph Learning from Educational Data // Proc of the 8th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2015: 159-168. [20] TATSUOKA K K.Boolean Algebra Applied to Determination of Universal Set of Knowledge States. Technical Report, RR-91-44-ONR. Princeton, USA: Educational Testing Service, 1991. [21] GUO L, BAO Y, WANG Z R, et al. Cognitive Diagnostic Assessment with Different Weight for Attribute: Based on the Dina Mo-del. Psychological Reports, 2014, 114(3): 802-822. [22] ZHANG S J, HUANG S, YU X H, et al. A Generalized Multi-skill Aggregation Method for Cognitive Diagnosis. World Wide Web, 2022. DOI: 10.1007/s11280-021-00990-4. [23] 张所娟,黄松,余晓晗,等.基于模糊测度的知识关联性建模方法.模式识别与人工智能, 2022, 35(2): 95-105. (ZHANG S J, HUANG S, YU X H, et al. Modeling Method of Knowledge Relevance Based on Fuzzy Measures. Pattern Recognition and Artificial Intelligence, 2022, 35(2): 95-105.) [24] ISLAM M A, ANDERSON D T, PINAR A J, et al. Enabling Explainable Fusion in Deep Learning with Fuzzy Integral Neural Net-works. IEEE Transactions on Fuzzy Systems, 2020, 28(7): 1291-1300. [25] ISLAM M A, ANDERSON D T, PINAR A J, et al. Data-Driven Compression and Efficient Learning of the Choquet Integral. IEEE Transactions on Fuzzy Systems, 2018, 26(4): 1908-1922. [26] BELIAKOV G, DIVAKOV D.Fitting Sugeno Integral for Learning Fuzzy Measures Using PAVA Isotone Regression. International Journal of Intelligent Systems, 2019, 34(11): 2863-2871. [27] YANG R, WANG Z Y, HENG P A, et al. Classification of Hetero-geneous Fuzzy Data by Choquet Integral with Fuzzy-Valued Integrand. IEEE Transactions on Fuzzy Systems, 2007, 15(5): 931-942. [28] JIN L S, KALINA M, MESIAR R, et al. Discrete Choquet Integrals for Riemann Integrable Inputs with Some Applications. IEEE Transactions on Fuzzy Systems, 2018, 26(5): 3164-3169. [29] GLOROT X, BENGIO Y.Understanding the Difficulty of Training Deep Feedforward Neural Networks // Proc of the 13th Internatio-nal Conference on Artificial Intelligence and Statistics. San Diego, USA: JMLR, 2010: 249-256. [30] SALAKHUTDINOV R, MNIH A.Probabilistic Matrix Factorization // Proc of the 21st International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2007: 1257-1264. [31] GRABISCH M.The Representation of Importance and Interaction of Features by Fuzzy Measures. Pattern Recognition Letters, 1996, 17(6): 567-575. |
|
|
|