<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This paper combines augmented learning algorithms and data mining techniques for an intelligent recommendation system for computer course projects to optimize the allocation of learning resources and improve learning efficiency and effectiveness. The research methodology includes an improved association rule mining algorithm and an augmented learning model applying deep Q-network and adaptive reward function. The research results show that the system can effectively mine knowledge point associations and achieve personalized recommendation. In particular, the accuracy of knowledge point associations and the customized level of recommendation are improved by multi-support strategy improvement and knowledge point association correction. Experiments show that on the edX dataset, the recommendation recall reaches 0.347 at k=10 and 0.433 at k=20, significantly better than the traditional recommendation algorithm. This intelligent recommendation system can effectively improve the learning effect of computer course projects, and it has a positive impact on both learning attitude and independent learning ability, especially helping the backward students significantly and reducing the learning differences between classes.</p>
</abstract>

This paper combines augmented learning algorithms and data mining techniques for an intelligent recommendation system for computer course projects to optimize the allocation of learning resources and improve learning efficiency and effectiveness. The research methodology includes an improved association rule mining algorithm and an augmented learning model applying deep Q-network and adaptive reward function. The research results show that the system can effectively mine knowledge point associations and achieve personalized recommendation. In particular, the accuracy of knowledge point associations and the customized level of recommendation are improved by multi-support strategy improvement and knowledge point association correction. Experiments show that on the edX dataset, the recommendation recall reaches 0.347 at k=10 and 0.433 at k=20, significantly better than the traditional recommendation algorithm. This intelligent recommendation system can effectively improve the learning effect of computer course projects, and it has a positive impact on both learning attitude and independent learning ability, especially helping the backward students significantly and reducing the learning differences between classes.

Research on Intelligent Recommendation of Computer Course Items Combining Augmented Learning Algorithms and Data Mining Techniques

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

This paper combines augmented learning algorithms and data mining techniques for an intelligent recommendation system for computer course projects to optimize...

Research on Intelligent Recommendation of Computer Course Items Combining Augmented Learning Algorithms and Data Mining Techniques

Pubblicato online: 26 feb 2024

Pagine: -

Ricevuto: 12 gen 2024

Accettato: 19 gen 2024

DOI: https://doi.org/10.2478/amns-2024-0517

Parole chiave
Augmented learning, Data mining, Intelligent recommender system, Computer course project

© 2024 Yanfei Zhao et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on Intelligent Recommendation of Computer Course Items Combining Augmented Learning Algorithms and Data Mining Techniques

Pubblicato online: 26 feb 2024

Pagine: -

Ricevuto: 12 gen 2024

Accettato: 19 gen 2024

DOI: https://doi.org/10.2478/amns-2024-0517

Parole chiaveAugmented learning, Data mining, Intelligent recommender system, Computer course project

© 2024 Yanfei Zhao et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Augmented learning, Data mining, Intelligent recommender system, Computer course project