计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (10): 170-177.doi: 10.11896/jsjkx.240300121

• 智能教育技术及应用 • 上一篇    下一篇

基于速度与准确率权衡的深度认知诊断模型

程艳1,2,3, 周子为2,3, 马明宇2,3, 林庆龙2,3, 詹勇鑫2,3, 万凌峰2,3   

  1. 1 江西师范大学软件学院 南昌 330022
    2 江西师范大学计算机信息工程学院 南昌 330022
    3 江西省智能信息处理与情感计算省重点实验室 南昌 330022
  • 收稿日期:2024-03-18 修回日期:2024-07-07 出版日期:2024-10-15 发布日期:2024-10-11
  • 通讯作者: 程艳(chyan88888@jxnu.edu.cn)
  • 基金资助:
    国家自然科学基金(62167006);江西省科技创新基地计划项目——智能信息处理与情感计算江西省重点实验室(2024SSY03131);江西省主要学科学术和技术带头人培养计划——领军人才项目(20213BCJL22047);江西省自然科学基金(20212BAB202017)

Speed-Accuracy Tradeoff-based Deep Cognitive Diagnostic Model

CHENG Yan1,2,3, ZHOU Ziwei2,3, MA Mingyu2,3, LIN Qinglong2,3, ZHAN Yongxin2,3, WAN Lingfeng2,3   

  1. 1 School of Software,Jiangxi Normal University,Nanchang 330022,China
    2 School of Computer Information Engineering,Jiangxi Normal University,Nanchang 330022,China
    3 Provincial Key Laboratory of Intelligent Information Processing and Affective Computing of Jiangxi Province,Nanchang 330022,China
  • Received:2024-03-18 Revised:2024-07-07 Online:2024-10-15 Published:2024-10-11
  • About author:CHEN Yan,born in 1976,Ph.D,professor,Ph.D supervisor.Her main reaserch interests include artificial intelligence education,deep learning and emotional computing,artificial intelligence and big data,intelligent information processing,etc.
  • Supported by:
    National Natural Science Foundation of China(62167006),Jiangxi Provincial Science and Technology Innovation Base Program Project－Jiangxi Provincial Key Laboratory of Intelligent Information Processing and Affective Computing(2024SSY03131),Jiangxi Province Leading Talent Project of Major Academic Disciplines and Technologies(20213BCJL22047) andNatural Science Foundation of Jiangxi Province,China(20212BAB202017).

PDF (PC)

249

摘要： 智能教育中,认知诊断通过分析学习者的学习行为数据来理解学习者的认知状态。现有基于深度学习方法的认知诊断模型默认假设学习者在作答过程中有足够的作答时间来完全发挥知识掌握水平,未考虑学习者在作答过程中的作答速度与作答准确率之间的权衡策略对发挥知识掌握水平的影响。针对上述问题,提出了一种基于速度与准确率权衡的深度认知诊断模型,首先构建认知风格模糊集解释学习者的权衡策略,然后通过动态逻辑回归函数模拟学习者作答过程中的速度与准确率权衡关系,实现对学习者理论上能达到最高的知识掌握水平与实际作答中发挥出来的知识掌握水平的区分诊断。此外还引入了作答时间属性和题目类型属性,以更准确地表征认知诊断交互函数中的题目参数。大量实验表明,该模型相比同类最优模型在3个公开数据集上准确度分别提升2.58%,2.86%,5.18%,且能为预测结果提供作答时间层面的解释,具有一定的优越性。

关键词: 智能教育, 深度认知诊断, 速度与准确率权衡, 模糊集, 逻辑回归函数

Abstract: In intelligent education,cognitive diagnosis analyzes students' learning behavior data to understand their cognitive state.Existing cognitive diagnostic models based on deep learning methods assume by default that students have enough reaction time to fully exert the level of knowledge mastery during the response process,and do not consider the impact of the trade-off strategy between the speed and accuracy of student's response during the response process on the exertion of the level of know-ledge mastery.Aiming at the above problem,a deep cognitive diagnostic model based on speed-accuracy trade-off is proposed,which firstly constructs a cognitive style fuzzy set to explain the students' trade-off strategy,and then simulates the speed-accuracy trade-off relationship in the process of the learners' response through the dynamic logistic regression function,so as to rea-lize the differentiated diagnosis of the students' theoretically highest level of knowledge mastery from the level of knowledge mastery they have played out in the actual response.In addition,the reaction time attribute and exercise type attribute are introduced to more accurately characterize the topic parameters in the cognitive diagnostic interaction function.Numerous experiments show that the model not only improves the accuracy by 2.58%,2.86%,and 5.18% compared to similar optimal models on the three publicly available datasets,but also provides a superior explanation of the prediction results at the level of response time.

Key words: Intelligent education, Deep cognitive diagnostics, Speed-Accuracy trade-off, Fuzzy sets, Logistic regression function

中图分类号: 

  • TP391
[1]JIA T,GU X Q.Data technology-driven reshaping of educational forms:paths and processes[J].China Educational Technology,2021(3):38-45.
[2]LUO Z S.Fundamentals of Cognitive Diagnostic Assessment[M].Beijing:Beijing Normal University Press,2019.
[3]EMBRETSON S E,REISE S P.Item response theory[M].Psychology Press,2013.
[4]DE LA TORRE J.DINA model and parameter estimation:A didactic[J].Journal of Educational and Behavioral Statistics,2009,34(1):115-130.
[5]RECKASE M D.The past and future of multidimensional item response theory[J].Applied Psychological Measurement,1997,21(1):25-36.
[6]DE LA TORRE J.The generalized DINA model framework[J].Psychometrika,2011,76:179-199.
[7]LIU Q.Towards a New Generation of Cognitive Diagnosis[C]//IJCAI.2021:4961-4964.
[8]LIU Q,WU R,CHEN E,et al.Fuzzy cognitive diagnosis for modelling examinee performance[J].ACM Transactions on Intelligent Systems and Technology(TIST),2018,9(4):1-26.
[9]CHENG S,LIU Q,CHEN E,et al.DIRT:Deep learning en-hanced item response theory for cognitive diagnosis[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management.2019:2397-2400.
[10]WANG F,LIU Q,CHEN E,et al.NeuralCD:A General Framework for Cognitive Diagnosis[J].IEEE Transactions on Know-ledge and Data Engineering,2023,35(8):8312-8327.
[11]MA H,LI M,WU L,et al.Knowledge-Sensed Cognitive Diagnosis for Intelligent Education Platforms[C]//Proceedings of the 31st ACM International Conference on Information & Know-ledge Management.2022:1451-1460.
[12]GUO X J,LUO Z S.Psychometric model and application based on speed-accuracy trade-offs[J].Psychological Exploration,2019,39(5):451-460.
[13]WICKELGREN W A.Speed-accuracy tradeoff and information processing dynamics[J].Acta Psychologica,1977,41(1):67-85.
[14]HEITZ R P.The speed-accuracy tradeoff:history,physiology,methodology,and behavior[J].Frontiers in Neuroscience,2014,8:150.
[15]REED A V.Speed-accuracy trade-off in recognition memory[J].Science,1973,181(4099):574-576.
[16]DONKIN C,LITTLE D R,HOUPT J W.Assessing the speed-accuracy trade-off effect on the capacity of information proces-sing[J].Journal of Experimental Psychology:Human Perception and Performance,2014,40(3):1183.
[17]RATCLIFF R,SMITH P L,BROWN S D,et al.Diffusion decision model:Current issues and history[J].Trends in Cognitive Sciences,2016,20(4):260-281.
[18]ZHU Y.Experimental Psychology(2nd ed.)[M].Beijing:Pe-king University Press,2009.
[19]ZHANG S J,YU X H,CHEN E H,et al.A Concept Interac-tion-Based Cognitive Diagnosis Deep Model[J].Pattern Recognition and Artificial Intelligence,2023,36(1):22-33.
[20]WANG W Y,SONG L H,DING S L.Cognitive Diagnostic Test Item Distinction Indicators and Applications from a Categorical Perspective[J].Psychological Science,2018,41(2):475-483.
[21]HE J,MAO X Z,TANG Q,et al.A dual-objective CD-CAT se-lection strategy based on item differentiation[J].Psychological Science,2022,45(1):204-212.
[22]GUO X J,LUO Z S.The speed-accuracy trade-off:evaluationand modeling of subjects' response states[J].Studies of Psycho-logy and Behavior,2019,17(5):589-595.
[23]YAN J H.Cognitive styles affect choice response time and accuracy[J].Personality and Individual Differences,2010(6):747-751.
[24]SULISAWATI D N,LUTFIYAH L,MURTINASARI F.Difference of mistakes reflective-impulsive students in mathematical problem solving[J].International Journal of Trends in Mathematics Education Research,2019(2):101-105.
[25]FENG M,HEFFERNAN N,KOEDINGER K.Addressing theassessment challenge with an online system that tutors as it assesses[J].User Modeling and User-Adapted Interaction,2009,19(3):243-266.
[26]LIU J Y,WANG F,MA H P,et al.A Probabilistic Framework for Temporal Cognitive Diagnosis in Online Learning Systems[J].Journal of Computer Science and Technology,2023,38(6):1203-1222.
[27]LI Y H,YANG X Y.Educational and Psychological Statistics[M].Jiangxi University Press,2020.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发