Knowledge Tracing Model Based on Multiple Behavior Features Embedded Memory Networks
Purposes A Knowledge Tracing Model based on Multiple Behavior Features Embedded Memory Networks (MFKT) was proposed to fully utilize the learning and forgetting features in interaction records. The MFKT model considers both learning and forgetting behaviors in the learning process. Methods First, tw...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Office of Journal of Taiyuan University of Technology
2024-01-01
|
| Series: | Taiyuan Ligong Daxue xuebao |
| Subjects: | |
| Online Access: | https://tyutjournal.tyut.edu.cn/englishpaper/show-2258.html |
| _version_ | 1797208301677576192 |
|---|---|
| author | Bugui HE Yongquan DONG Rui JIA Jiayong JIN |
| author_facet | Bugui HE Yongquan DONG Rui JIA Jiayong JIN |
| author_sort | Bugui HE |
| collection | DOAJ |
| description | Purposes A Knowledge Tracing Model based on Multiple Behavior Features Embedded Memory Networks (MFKT) was proposed to fully utilize the learning and forgetting features in interaction records. The MFKT model considers both learning and forgetting behaviors in the learning process. Methods First, two major features, learning and forgetting, are extracted from the interaction records, and then the extracted learning features are embedded into the memory network by scalar crossover, while the forgetting features are embedded by vector combination, which is used to enhance the learning ability of MFKT model for the students’ interaction sequences. In addition, after different students’ answers are completed, the difference in knowledge level growth is considered and a knowledge growth layer to the original memory network is added for calculating the knowledge growth obtained from students’ responses. Conclusion Experiment results on public datasets show that MFKT is more in line with real learning patterns of students and can realize more accurate tracing of students’ knowledge status. |
| first_indexed | 2024-04-24T09:36:38Z |
| format | Article |
| id | doaj.art-93bc2de309ea4d388f13fd92365c74a8 |
| institution | Directory Open Access Journal |
| issn | 1007-9432 |
| language | English |
| last_indexed | 2024-04-24T09:36:38Z |
| publishDate | 2024-01-01 |
| publisher | Editorial Office of Journal of Taiyuan University of Technology |
| record_format | Article |
| series | Taiyuan Ligong Daxue xuebao |
| spelling | doaj.art-93bc2de309ea4d388f13fd92365c74a82024-04-15T09:17:22ZengEditorial Office of Journal of Taiyuan University of TechnologyTaiyuan Ligong Daxue xuebao1007-94322024-01-0155118419410.16355/j.tyut.1007-9432.2023BD0081007-9432(2024)01-0184-11Knowledge Tracing Model Based on Multiple Behavior Features Embedded Memory NetworksBugui HE0Yongquan DONG1Rui JIA2Jiayong JIN3College of Computer Science and Technology, Jiangsu Normal University, Xuzhou 221116, ChinaCollege of Computer Science and Technology, Jiangsu Normal University, Xuzhou 221116, ChinaCollege of Computer Science and Technology, Jiangsu Normal University, Xuzhou 221116, ChinaCollege of Computer Science and Technology, Jiangsu Normal University, Xuzhou 221116, ChinaPurposes A Knowledge Tracing Model based on Multiple Behavior Features Embedded Memory Networks (MFKT) was proposed to fully utilize the learning and forgetting features in interaction records. The MFKT model considers both learning and forgetting behaviors in the learning process. Methods First, two major features, learning and forgetting, are extracted from the interaction records, and then the extracted learning features are embedded into the memory network by scalar crossover, while the forgetting features are embedded by vector combination, which is used to enhance the learning ability of MFKT model for the students’ interaction sequences. In addition, after different students’ answers are completed, the difference in knowledge level growth is considered and a knowledge growth layer to the original memory network is added for calculating the knowledge growth obtained from students’ responses. Conclusion Experiment results on public datasets show that MFKT is more in line with real learning patterns of students and can realize more accurate tracing of students’ knowledge status.https://tyutjournal.tyut.edu.cn/englishpaper/show-2258.htmlintelligent educationknowledge tracingfeature extractiondynamic key-value memory networkslearning and forgetting |
| spellingShingle | Bugui HE Yongquan DONG Rui JIA Jiayong JIN Knowledge Tracing Model Based on Multiple Behavior Features Embedded Memory Networks Taiyuan Ligong Daxue xuebao intelligent education knowledge tracing feature extraction dynamic key-value memory networks learning and forgetting |
| title | Knowledge Tracing Model Based on Multiple Behavior Features Embedded Memory Networks |
| title_full | Knowledge Tracing Model Based on Multiple Behavior Features Embedded Memory Networks |
| title_fullStr | Knowledge Tracing Model Based on Multiple Behavior Features Embedded Memory Networks |
| title_full_unstemmed | Knowledge Tracing Model Based on Multiple Behavior Features Embedded Memory Networks |
| title_short | Knowledge Tracing Model Based on Multiple Behavior Features Embedded Memory Networks |
| title_sort | knowledge tracing model based on multiple behavior features embedded memory networks |
| topic | intelligent education knowledge tracing feature extraction dynamic key-value memory networks learning and forgetting |
| url | https://tyutjournal.tyut.edu.cn/englishpaper/show-2258.html |
| work_keys_str_mv | AT buguihe knowledgetracingmodelbasedonmultiplebehaviorfeaturesembeddedmemorynetworks AT yongquandong knowledgetracingmodelbasedonmultiplebehaviorfeaturesembeddedmemorynetworks AT ruijia knowledgetracingmodelbasedonmultiplebehaviorfeaturesembeddedmemorynetworks AT jiayongjin knowledgetracingmodelbasedonmultiplebehaviorfeaturesembeddedmemorynetworks |