The week's pick
Random Articles
Reseach Article
Artificial Intelligence (AI) - based Driven technique for Marking and Grading of Essay Handwriting Examination Scripts in Tertiary Institution
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 141 |
| Year of Publication: 2026 |
| Authors: Blessing Olawale Olasunkanmi, Sadiq Fatai Idowu, Joshua Tom, Oyekanmi O. Ezekiel, Sunday Ebenezer Adepoju, Abe Oluwaseyi Olugbenga |
10.5120/ijca6dcd7bf0f859
|
Blessing Olawale Olasunkanmi, Sadiq Fatai Idowu, Joshua Tom, Oyekanmi O. Ezekiel, Sunday Ebenezer Adepoju, Abe Oluwaseyi Olugbenga . Artificial Intelligence (AI) - based Driven technique for Marking and Grading of Essay Handwriting Examination Scripts in Tertiary Institution. International Journal of Computer Applications. 187, 141 ( Sep 2026), 67-74. DOI=10.5120/ijca6dcd7bf0f859
Abstract
Manual grading of essay handwritten examination scripts is time-consuming, subject to grader fatigue, and prone to inter-rater inconsistency, particularly when class size is large. This study addressed these challenges by proposing an AI-based technique for marking and grading essay handwritten examination scripts, using a deterministic rule-based engine for multiple choice questions (MCQ) alongside a Gemini 2.5 Flash large language model guided by structured prompts and marking rubrics for theory questions. A two-phase model converted physical handwritten scripts into digital structure for AI evaluation, while a multi-strategy javaScript object notation (JSON) parsing approach extracted and validated structured data using natural language processing (NLP) and deep learning methods. The paper adopted a tri-instance pipeline handling marking-guide extraction and handwritten script transcription for grading, evaluated against human-expert scores using a double-blind design to eliminate anchoring and confirmation bias. The system was tested on forty (40) handwritten scripts, twenty (20) from CSC 307 (Compiler Construction) and twenty (20) from CSC 405 ("Computer Graphics"), collected from the Department of Computer Science, Ambrose Ali University, Ekpoma (AAUE). The digitization pipeline achieved a 100% processing success rate with 300 DPI rasterization. Comparison with human-expert scores yielded a combined Pearson correlation of r = 0.5237 (CSC 405: r = 0.595; CSC 307: r = 0.556), which shows a moderate positive relationship that preserves relative ranking of student performance. The develop AI-driven technique is technically feasible and can complements traditional grading methods for marking and grading essay handwriting of examination scripts.
References
- Adeyanju, I. A., Oderinde, K. R., Adedeji, O. T., Gbadamosi, O. A., Makinde, B. O., & Falohun, A. S. (2024). Artificial Intelligence Based Essay Grading System. Engineering and Technology Journal, 9(7), 4382-4388.Attali, Y., & Burstein, J. (2006). Automated essay scoring with e-rater v.2. Journal of Technology, Learning, and Assessment, 4(3).
- Bai, Y., Lv, X., Zhang, J., Xie, Peng., & Li, J. (2025). LongBench v2: Towards multi-task and long-context evaluation for large language models. arXiv preprint arXiv:2412.15204.
- Dada, I. D., Akinwale, A. T., & Tunde-Adeleke, T.-J. (2025). A Structured Dataset for Automated Grading: From Raw Data to Processed Dataset. Data, 10(6), 87.
- Faseeh, M., Jaleel, A., Iqbal, N., Ghani, A., Abdusalomov, A., Mehmood, A., & Cho, Y.-I. (2024). Hybrid Approach to Automated Essay Scoring. Mathematics, 12(21), 3416.
- Foltz, P., Laham, D., & Landauer, T. (1999). The intelligent essay assessor: Applications to educational technology. Interactive Multimedia Electronic Journal of Computer-Enhanced Learning.
- Gause G, Mokgaola IO, Rakhudu MA. (2022). Technology usage for teaching and learning in nursing education: An integrative review. Curationis. 2022 Jun 15;45(1):e1 e9. doi: 10.4102/curationis.v45i1.2261.
- Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780.
- Lewis Sevcikova, B. (2018). Human versus Automated Essay Scoring: A Critical Review. Arab World English Journal, 9(2).
- Mena-Guacas, A. F., López-Catalán, L., Bernal-Bravo, C., & Ballesteros-Regaña, C. (2025). Educational Transformation Through Emerging Technologies: Critical Review of Scientific Impact on Learning. Education Sciences, 15(3), 368. https://doi.org/10.3390/educsci15030368 Misgna, H., & Haile, A. (2026). LEAF++: Trait-annotated essay feedback dataset with validation of trait scores via LLMs. IEEE Access, 14, 11303–11315. https://doi.org/10.1109/ACCESS.2026.11303736.
- Misgna, H., & Haile, A. (2026). LEAF++: Trait-annotated essay feedback dataset with validation of trait scores via LLMs. IEEE Access, 14, 11303–11315. https://doi.org/10.1109/ACCESS.2026.11303736
- Obot, O. U., Obike, P., & James, I. (2024). Automated Marking System for Essay Questions. Journal of Engineering Research and Reports, 26(5), 107-126.
- Page, E. B. (1966). The imminence of grading essays by computer. Phi Delta Kappan, 47, 238-243.
- Ramesh, D., & Sanampudi, S. K. (2022). An automated essay scoring systems: A systematic literature review. Artificial Intelligence Review, 55(3), 2495-2527.
- Shermis, M. D., & Hamner, B. (2012). Contrasting state-of-the-art automated scoring of essays. In Handbook of Automated Essay Evaluation.
- Taghipour, K., & Ng, H. T. (2016). A neural approach to automated essay scoring. Proceedings of EMNLP.
- Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
Index Terms
Keywords