Please use this identifier to cite or link to this item:
https://repository.isls.org/handle/1/8544| Title: | Comparative Analysis of the Rule-Based and Machine Learning Approach for Assessing Student Reflections |
| Authors: | Butt, Ahmed Ashraf Anwar, Saira Magooda, Ahmed Menekse, Muhsin |
| Keywords: | Learning Sciences |
| Issue Date: | 2022 |
| Publisher: | International Society of the Learning Sciences |
| Citation: | Butt, A. A., Anwar, S., Magooda, A., & Menekse, M. (2022). Comparative analysis of the rule-based and machine learning approach for assessing student reflections. In Chinn, C., Tan, E., Chan, C., & Kali, Y. (Eds.), Proceedings of the 16th International Conference of the Learning Sciences - ICLS 2022 (pp. 1577-1580). International Society of the Learning Sciences. |
| Abstract: | This study describes Natural Language Processing (NLP) and rule-based algorithms used to assess the students’ written reflection quality. We used the CourseMIRROR application to gather student reflections from 120 engineering students and converted the reflections into an equivalent quality score using human coders and algorithms. We used Cohen’s kappa statistics to explore the agreement between the algorithm’s reflection quality and the human coding. The results revealed a strong agreement between the NLP algorithm and human coding. Furthermore, we used Spearman correlation statistics to evaluate the relationship between the predicted quality scores and the human coding. The results showed a strong correlation between reflection quality evaluated by the NLP algorithm and human coders. Overall results revealed that the NLP algorithm embedded in the CourseMIRROR application is a good fit for assessing students’ reflections and can be used to guide them during the reflection writing process. |
| Description: | Short Paper |
| URI: | https://dx.doi.org/10.22318/icls2022.1577 https://repository.isls.org//handle/1/8544 |
| Appears in Collections: | ISLS Annual Meeting 2022 |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ICLS2022_1577-1580.pdf | 246.17 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.