Please use this identifier to cite or link to this item:
https://repository.isls.org/handle/1/10075| Title: | A Systematic Review of Automated Feedback Generation in Empirical Educational Research |
| Authors: | Song, Yajie Jin, Hao-Yue Pan, Zexuan Cutumisu, Maria |
| Keywords: | Learning Sciences |
| Issue Date: | 2023 |
| Publisher: | International Society of the Learning Sciences |
| Citation: | Song, Y., Jin, H., Pan, Z., & Cutumisu, M. (2023). A systematic review of automated feedback generation in empirical educational research. In Blikstein, P., Van Aalst, J., Kizito, R., & Brennan, K. (Eds.), Proceedings of the 17th International Conference of the Learning Sciences - ICLS 2023 (pp. 1895-1896). International Society of the Learning Sciences. |
| Abstract: | Automated Feedback Generation (AFG) has gained much attention as a way to revolutionize online feedback provision. This paper reviews 30 publications to systematically analyze the effectiveness of AFG in empirical educational research. Pre-defined templates, natural language processing, and comparison with correct answers are commonly used AFG methods. Results show that AFG positively impacts student learning and feedback quality. However, gaps in current AFG research were identified, and suggestions for improvement include expanding the use of AFG from higher education to K-12 education. |
| Description: | Poster |
| URI: | https://doi.org/10.22318/icls2023.403455 https://repository.isls.org//handle/1/10075 |
| Appears in Collections: | ISLS Annual Meeting 2023 |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ICLS2023_1895-1896.pdf | 75.7 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.