Development of an automated grading system based on Office Open XML, rubric JSONs, and AI-assisted feedback for a general informatics course
Article Sidebar
Main Article Content
Development of an automated grading system based on Office Open XML, rubric JSONs, and AI-assisted feedback for a general informatics course
Abstract
This study presents the development and evaluation of an Automated Grading System (AGS) for Microsoft Word, Excel, and PowerPoint practical assignments in a General Informatics course. The system analyzes the Office Open XML structures of .docx, .xlsx, and .pptx files, normalizes the extracted data into a JSON-based abstract syntax tree (JSON AST), locates assessment objects using an Anchor Locator, and executes criteria represented as JSON Rubrics through a Rule Engine. The workflow is orchestrated on the n8n platform, while a large language model is used only to interpret results and generate feedback rather than to determine scores directly. The initial dataset comprised 1,374 submissions. After invalid and duplicate files were removed, 1,257 submissions were processed, of which 1,247 complete instructor–AGS score pairs were included in the analysis. The overall mean absolute error was 0.618 points on a 10-point scale; 84.4% of the automated scores differed from the instructor’s scores by no more than one point, and the mean bias was −0.051 points. Excel produced the lowest absolute discrepancy. Analysis of 204 cases requiring review showed that discrepancies were mainly associated with the system’s failure to recognize valid alternative implementations or with grading rules that did not fully verify the required techniques. The findings demonstrate the feasibility and traceability of a unified grading architecture while also highlighting the continued importance of instructor oversight for exceptional cases.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
- Ecma International. (2021). Office Open XML file formats (5th ed.; Standard ECMA-376). https://ecma-international.org/publications-and-standards/standards/ecma-376/
- Gao, R., Merzdorf, H. E., Anwar, S., Hipwell, M. C., & Srinivasa, A. R. (2024). Automatic assessment of text-based responses in post-secondary education: A systematic review. Computers and Education: Artificial Intelligence, 6, Article 100206. https://doi.org/10.1016/j.caeai.2024.100206
- Hekman, K. (2019, June). Automated grading of Microsoft Excel spreadsheets. In 2019 ASEE Annual Conference & Exposition. American Society for Engineering Education. https://doi.org/10.18260/1-2--32135
- Hunnicutt, S. S. (2016). An automated grading spreadsheet for reports or presentations. Journal of Chemical Education, 93(1), 210–212. https://doi.org/10.1021/acs.jchemed.5b00553
- International Organization for Standardization. (2021). Document description and processing languages—Office Open XML file formats—Part 2: Open packaging conventions (ISO/IEC Standard No. 29500-2:2021). https://www.iso.org/standard/77818.html
- Iwata, K., & Matsui, Y. (2022). Implementation of an automated grading system for Microsoft Excel spreadsheets and Word documents. In T. Matsuo (Ed.), Proceedings of the 11th International Congress on Advanced Applied Informatics (EPiC Series in Computing, Vol. 81, pp. 289–302). EasyChair. https://doi.org/10.29007/1zs6
- Jonsson, A., & Svingby, G. (2007). The use of scoring rubrics: Reliability, validity and educational consequences. Educational Research Review, 2(2), 130–144. https://doi.org/10.1016/j.edurev.2007.05.002
- Kovačić, Z. J., & Green, J. S. (2012). Automatic grading of spreadsheet and database skills. Journal of Information Technology Education: Innovations in Practice, 11, 53–70. https://www.jite.org/documents/Vol11/JITEv11IIPp053-070Kovacic1051.pdf
- Messer, M., Brown, N. C. C., Kölling, M., & Shi, M. (2024). Automated grading and feedback tools for programming education: A systematic review. ACM Transactions on Computing Education, 24(1), Article 10, 1–43. https://doi.org/10.1145/3636515
- Padó, U., Eryilmaz, Y., & Kirschner, L. (2024). Short-answer grading for German: Addressing the challenges. International Journal of Artificial Intelligence in Education, 34(4), 1321–1352. https://doi.org/10.1007/s40593-023-00383-w
- Panadero, E. (2020). A critical review of the arguments against the use of rubrics. Educational Research Review, 30, Article 100329. https://doi.org/10.1016/j.edurev.2020.100329
- Panadero, E., & Jonsson, A. (2013). The use of scoring rubrics for formative assessment purposes revisited: A review. Educational Research Review, 9, 129–144. https://doi.org/10.1016/j.edurev.2013.01.002
- Pecuchova, J., Benko, Ľ., & Drlík, M. (2025). Automated grading of open-ended questions in higher education using GenAI models. International Journal of Artificial Intelligence in Education, 35(6), 3813–3846. https://doi.org/10.1007/s40593-025-00517-2
- Rezaei, A. R., & Lovorn, M. (2010). Reliability and validity of rubrics for assessment through writing. Assessing Writing, 15(1), 18–39. https://doi.org/10.1016/j.asw.2010.01.003
- Sembey, R., Hoda, R., & Grundy, J. (2024). Emerging technologies in higher education assessment and feedback practices: A systematic literature review. Journal of Systems and Software, 211, Article 111988. https://doi.org/10.1016/j.jss.2024.111988