Advancing Educational Content Classification via Reinforcement Learning-Integrated Bloom's Taxonomy
Paper
Shaik, Thanveer, Tao, Xiaohui, Li, Lin, Dann, Christopher, Sun, Yuan and Sun, Yi. 2024. "Advancing Educational Content Classification via Reinforcement Learning-Integrated Bloom's Taxonomy." 2023 3rd International Conference on Digital Society and Intelligent Systems (DSInS). Chengdu, China 10 202 - 12 Nov 2023 IEEE (Institute of Electrical and Electronics Engineers). https://doi.org/10.1109/DSInS60115.2023.10455310
| Paper/Presentation Title | Advancing Educational Content Classification via Reinforcement Learning-Integrated Bloom's Taxonomy |
|---|---|
| Presentation Type | Paper |
| Authors | Shaik, Thanveer, Tao, Xiaohui, Li, Lin, Dann, Christopher, Sun, Yuan and Sun, Yi |
| Journal or Proceedings Title | Proceedings of 2023 3rd International Conference on Digital Society and Intelligent Systems (DSInS) |
| Journal Citation | pp. 8-13 |
| Number of Pages | 6 |
| Year | 2024 |
| Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
| ISBN | 9798350331387 |
| 9798350331370 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1109/DSInS60115.2023.10455310 |
| Web Address (URL) of Paper | https://ieeexplore.ieee.org/document/10455310 |
| Web Address (URL) of Conference Proceedings | https://ieeexplore.ieee.org/xpl/conhome/10455090/proceeding |
| Conference/Event | 2023 3rd International Conference on Digital Society and Intelligent Systems (DSInS) |
| Event Details | 2023 3rd International Conference on Digital Society and Intelligent Systems (DSInS) Delivery In person Event Date 10 Nov 0202 to end of 12 Nov 2023 Event Location Chengdu, China |
| Abstract | The digital evolution of education has highlighted the transformative potential of artificial intelligence (AI) in reshaping teaching and learning practices. This paper presents a groundbreaking methodology that combines the capabilities of reinforcement learning with the depth of multimodal data analysis, aiming to accurately categorize educational content according to Bloom’s Taxonomy. Despite the advancements in AI-based educational tools, challenges remain in ensuring precise and contextually relevant taxonomy level classifications. Our proposed approach addresses these issues by capitalizing on the sequential decision-making power of reinforcement learning, as well as the comprehensive nature of multimodal data. This methodology is executed through systematic data collection and representation, thoughtful configuration of reinforcement learning algorithms, and rigorous agent training. Two case studies serve to underline its efficacy: the first offers sophisticated insights for refining curriculum design, while the second demonstrates the system’s ability to adaptively select appropriate taxonomy levels. This innovation not only provides educators with data-driven resources but also fosters a unique synergy between human expertise and AI-generated insights, thereby enhancing pedagogical decisions and marking a significant stride toward a future of data-informed education. |
| Keywords | AI in Education; Bloom’s Taxonomy; Reinforcement Learning |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 460205. Intelligent robotics |
| 460804. Computing education | |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | School of Mathematics, Physics and Computing |
| Wuhan University of Technology, China | |
| School of Education | |
| National Institute of Informatics Library, Japan | |
| University of Academic of Sciences, China |
Permalink -
https://research.usq.edu.au/item/zq42q/advancing-educational-content-classification-via-reinforcement-learning-integrated-bloom-s-taxonomy
5
total views1
total downloads5
views this month1
downloads this month