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...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , , |
| 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 |