DKVMN&MRI model diagram.

<div><p>Knowledge tracing is a technology that models students’ changing knowledge state over learning time based on their historical answer records, thus predicting their learning ability. It is the core module that supports the intelligent education system. To address the problems of s...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Feng Xu (89016) (author)
مؤلفون آخرون: Kang Chen (285159) (author), Maosheng Zhong (6159869) (author), Lei Liu (5074) (author), Huizhu Liu (17133686) (author), Xianzeng Luo (19976674) (author), Lang Zheng (11461955) (author)
منشور في: 2024
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852025549274218496
author Feng Xu (89016)
author2 Kang Chen (285159)
Maosheng Zhong (6159869)
Lei Liu (5074)
Huizhu Liu (17133686)
Xianzeng Luo (19976674)
Lang Zheng (11461955)
author2_role author
author
author
author
author
author
author_facet Feng Xu (89016)
Kang Chen (285159)
Maosheng Zhong (6159869)
Lei Liu (5074)
Huizhu Liu (17133686)
Xianzeng Luo (19976674)
Lang Zheng (11461955)
author_role author
dc.creator.none.fl_str_mv Feng Xu (89016)
Kang Chen (285159)
Maosheng Zhong (6159869)
Lei Liu (5074)
Huizhu Liu (17133686)
Xianzeng Luo (19976674)
Lang Zheng (11461955)
dc.date.none.fl_str_mv 2024-10-30T17:30:57Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0312022.g002
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/DKVMN_MRI_model_diagram_/27345727
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Sociology
Science Policy
Biological Sciences not elsewhere classified
subsequent time step
study provides explanations
item response theory
intelligent education system
historical answer records
acc metrics contrast
value memory network
sparse input data
learners &# 8217
dkvmn incorporating multi
changing knowledge state
knowledge point relations
learning time based
knowledge state
memory forgetting
knowledge points
input layer
forgetting relations
world datasets
weak capacity
thus predicting
three real
significant improvements
prediction strategies
paper build
mri based
learning ability
latest models
improved dkvmn
extensive experiments
existing models
exercise relations
dynamic key
core module
attention mechanism
dc.title.none.fl_str_mv DKVMN&MRI model diagram.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>Knowledge tracing is a technology that models students’ changing knowledge state over learning time based on their historical answer records, thus predicting their learning ability. It is the core module that supports the intelligent education system. To address the problems of sparse input data, lack of interpretability and weak capacity to capture the relationship between exercises in the existing models, this paper build a deep knowledge tracing model DKVMN&MRI based on the Dynamic Key-Value Memory Network (DKVMN) that incorporates multiple relationship information including exercise-knowledge point relations, exercise-exercise relations, and learning-forgetting relations. In the model, firstly, the Q-matrix is utilized to map the link between knowledge points and exercises to the input layer; secondly, improved DKVMN and LSTM are used to model the learning process of learners, then the Ebbinghaus forgetting curve function is introduced to simulate the process of memory forgetting in learners, and finally, the prediction strategies of Item Response Theory (IRT) and attention mechanism are used to combine the similarity relationship between learners’ knowledge state and exercises to calculate the probability that learners would correctly respond during the subsequent time step. Through extensive experiments on three real-world datasets, we demonstrate that DKVMN&MRI has significant improvements in both AUC and ACC metrics contrast with the latest models. Furthermore, the study provides explanations at both the exercise level and learner knowledge state level, demonstrating the interpretability and efficacy of the proposed model.</p></div>
eu_rights_str_mv openAccess
id Manara_a653b529ef8a3cda0783feb5b3f8a204
identifier_str_mv 10.1371/journal.pone.0312022.g002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/27345727
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling DKVMN&MRI model diagram.Feng Xu (89016)Kang Chen (285159)Maosheng Zhong (6159869)Lei Liu (5074)Huizhu Liu (17133686)Xianzeng Luo (19976674)Lang Zheng (11461955)SociologyScience PolicyBiological Sciences not elsewhere classifiedsubsequent time stepstudy provides explanationsitem response theoryintelligent education systemhistorical answer recordsacc metrics contrastvalue memory networksparse input datalearners &# 8217dkvmn incorporating multichanging knowledge stateknowledge point relationslearning time basedknowledge statememory forgettingknowledge pointsinput layerforgetting relationsworld datasetsweak capacitythus predictingthree realsignificant improvementsprediction strategiespaper buildmri basedlearning abilitylatest modelsimproved dkvmnextensive experimentsexisting modelsexercise relationsdynamic keycore moduleattention mechanism<div><p>Knowledge tracing is a technology that models students’ changing knowledge state over learning time based on their historical answer records, thus predicting their learning ability. It is the core module that supports the intelligent education system. To address the problems of sparse input data, lack of interpretability and weak capacity to capture the relationship between exercises in the existing models, this paper build a deep knowledge tracing model DKVMN&MRI based on the Dynamic Key-Value Memory Network (DKVMN) that incorporates multiple relationship information including exercise-knowledge point relations, exercise-exercise relations, and learning-forgetting relations. In the model, firstly, the Q-matrix is utilized to map the link between knowledge points and exercises to the input layer; secondly, improved DKVMN and LSTM are used to model the learning process of learners, then the Ebbinghaus forgetting curve function is introduced to simulate the process of memory forgetting in learners, and finally, the prediction strategies of Item Response Theory (IRT) and attention mechanism are used to combine the similarity relationship between learners’ knowledge state and exercises to calculate the probability that learners would correctly respond during the subsequent time step. Through extensive experiments on three real-world datasets, we demonstrate that DKVMN&MRI has significant improvements in both AUC and ACC metrics contrast with the latest models. Furthermore, the study provides explanations at both the exercise level and learner knowledge state level, demonstrating the interpretability and efficacy of the proposed model.</p></div>2024-10-30T17:30:57ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0312022.g002https://figshare.com/articles/figure/DKVMN_MRI_model_diagram_/27345727CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/273457272024-10-30T17:30:57Z
spellingShingle DKVMN&MRI model diagram.
Feng Xu (89016)
Sociology
Science Policy
Biological Sciences not elsewhere classified
subsequent time step
study provides explanations
item response theory
intelligent education system
historical answer records
acc metrics contrast
value memory network
sparse input data
learners &# 8217
dkvmn incorporating multi
changing knowledge state
knowledge point relations
learning time based
knowledge state
memory forgetting
knowledge points
input layer
forgetting relations
world datasets
weak capacity
thus predicting
three real
significant improvements
prediction strategies
paper build
mri based
learning ability
latest models
improved dkvmn
extensive experiments
existing models
exercise relations
dynamic key
core module
attention mechanism
status_str publishedVersion
title DKVMN&MRI model diagram.
title_full DKVMN&MRI model diagram.
title_fullStr DKVMN&MRI model diagram.
title_full_unstemmed DKVMN&MRI model diagram.
title_short DKVMN&MRI model diagram.
title_sort DKVMN&MRI model diagram.
topic Sociology
Science Policy
Biological Sciences not elsewhere classified
subsequent time step
study provides explanations
item response theory
intelligent education system
historical answer records
acc metrics contrast
value memory network
sparse input data
learners &# 8217
dkvmn incorporating multi
changing knowledge state
knowledge point relations
learning time based
knowledge state
memory forgetting
knowledge points
input layer
forgetting relations
world datasets
weak capacity
thus predicting
three real
significant improvements
prediction strategies
paper build
mri based
learning ability
latest models
improved dkvmn
extensive experiments
existing models
exercise relations
dynamic key
core module
attention mechanism