Deep Learning Recommendations of E-Education Based on Clustering and Sequence
Commercial e-learning platforms have to overcome the challenge of resource overload and find the most suitable material for educators using a recommendation system (RS) when an exponential increase occurs in the amount of available online educational resources. Therefore, we propose a novel DNN meth...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/4/809 |
| _version_ | 1797621344427311104 |
|---|---|
| author | Furkat Safarov Alpamis Kutlimuratov Akmalbek Bobomirzaevich Abdusalomov Rashid Nasimov Young-Im Cho |
| author_facet | Furkat Safarov Alpamis Kutlimuratov Akmalbek Bobomirzaevich Abdusalomov Rashid Nasimov Young-Im Cho |
| author_sort | Furkat Safarov |
| collection | DOAJ |
| description | Commercial e-learning platforms have to overcome the challenge of resource overload and find the most suitable material for educators using a recommendation system (RS) when an exponential increase occurs in the amount of available online educational resources. Therefore, we propose a novel DNN method that combines synchronous sequences and heterogeneous features to more accurately generate candidates in e-learning platforms that face an exponential increase in the number of available online educational courses and learners. Mitigating the learners’ cold-start problem was also taken into consideration during the modeling. Grouping learners in the first phase, and combining sequence and heterogeneous data as embeddings into recommendations using deep neural networks, are the main concepts of the proposed approach. Empirical results confirmed the proposed solution’s potential. In particular, the precision rates were equal to 0.626 and 0.492 in the cases of Top-1 and Top-5 courses, respectively. Learners’ cold-start errors were 0.618 and 0.697 for 25 and 50 new learners. |
| first_indexed | 2024-03-11T08:54:38Z |
| format | Article |
| id | doaj.art-180fda3c17cc42c89fc9e090031d11d4 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T08:54:38Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-180fda3c17cc42c89fc9e090031d11d42023-11-16T20:10:21ZengMDPI AGElectronics2079-92922023-02-0112480910.3390/electronics12040809Deep Learning Recommendations of E-Education Based on Clustering and SequenceFurkat Safarov0Alpamis Kutlimuratov1Akmalbek Bobomirzaevich Abdusalomov2Rashid Nasimov3Young-Im Cho4Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of KoreaDepartment of AI Software, Gachon University, Seongnam-si 13120, Republic of KoreaDepartment of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of KoreaDepartment of Artificial Intelligence, Tashkent State University of Economics, Tashkent 100066, UzbekistanDepartment of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of KoreaCommercial e-learning platforms have to overcome the challenge of resource overload and find the most suitable material for educators using a recommendation system (RS) when an exponential increase occurs in the amount of available online educational resources. Therefore, we propose a novel DNN method that combines synchronous sequences and heterogeneous features to more accurately generate candidates in e-learning platforms that face an exponential increase in the number of available online educational courses and learners. Mitigating the learners’ cold-start problem was also taken into consideration during the modeling. Grouping learners in the first phase, and combining sequence and heterogeneous data as embeddings into recommendations using deep neural networks, are the main concepts of the proposed approach. Empirical results confirmed the proposed solution’s potential. In particular, the precision rates were equal to 0.626 and 0.492 in the cases of Top-1 and Top-5 courses, respectively. Learners’ cold-start errors were 0.618 and 0.697 for 25 and 50 new learners.https://www.mdpi.com/2079-9292/12/4/809recommendation systemmodelingsequence-awaredeep learningembedding |
| spellingShingle | Furkat Safarov Alpamis Kutlimuratov Akmalbek Bobomirzaevich Abdusalomov Rashid Nasimov Young-Im Cho Deep Learning Recommendations of E-Education Based on Clustering and Sequence Electronics recommendation system modeling sequence-aware deep learning embedding |
| title | Deep Learning Recommendations of E-Education Based on Clustering and Sequence |
| title_full | Deep Learning Recommendations of E-Education Based on Clustering and Sequence |
| title_fullStr | Deep Learning Recommendations of E-Education Based on Clustering and Sequence |
| title_full_unstemmed | Deep Learning Recommendations of E-Education Based on Clustering and Sequence |
| title_short | Deep Learning Recommendations of E-Education Based on Clustering and Sequence |
| title_sort | deep learning recommendations of e education based on clustering and sequence |
| topic | recommendation system modeling sequence-aware deep learning embedding |
| url | https://www.mdpi.com/2079-9292/12/4/809 |
| work_keys_str_mv | AT furkatsafarov deeplearningrecommendationsofeeducationbasedonclusteringandsequence AT alpamiskutlimuratov deeplearningrecommendationsofeeducationbasedonclusteringandsequence AT akmalbekbobomirzaevichabdusalomov deeplearningrecommendationsofeeducationbasedonclusteringandsequence AT rashidnasimov deeplearningrecommendationsofeeducationbasedonclusteringandsequence AT youngimcho deeplearningrecommendationsofeeducationbasedonclusteringandsequence |