Rudragouda G. Patil; Mahantesh N. Birje; Manisha Tapale; Nagaraj V. Dharwadkar

AI-Driven Rubrics for Academic Grading & Feedback Using Fuzzy Clustering & Attention Networks

PDF (1734KB), PP.1-24

Views: 0 Downloads: 0

Author(s)

Rudragouda G. Patil ^1,2,* Mahantesh N. Birje ¹ Manisha Tapale ³ Nagaraj V. Dharwadkar ⁴

1. Department of Computer Science and Engineering, Visvesvaraya Technological University, Belagavi-590018, Karnataka, India

2. Department of Computer Engineering, Marathwada Mitramandal’s College of Engineering, Pune 511052, MH, India

3. Department of Computer Science and Engineering, KLE Technological University Dr. MSSCET, Belagavi-590018, Karnataka, India

4. Department of Computer Science, Central University of Karnataka (CUK), Kadaganchi, Kalaburgi-585367, Karnataka, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijmecs.2026.04.01

Received: 25 Sep. 2025 / Revised: 10 Dec. 2025 / Accepted: 12 Feb. 2026 / Published: 8 Aug. 2026

Index Terms

Grade Prediction, Dynamic Rubrics, Fuzzy Clustering, Foraging Phase Updated Addax Optimization, Generative Attention Long Short Term Memory

Abstract

Educational assessment has changed from “one size fits all” model to learner-centered, responsive, and adaptable dynamic rubrics and feedback procedures. Improved instructor-student communication and transparency boost, engagement and assessment confidence with dynamic rubrics. Dynamic rubrics could improve feedback and assessment. Pre-processed standard dataset texts are used. Pre-processed texts are delivered to Word2Vec to extract key features and vectorize them. Fuzzy clustering model with dynamically weighted rubrics evaluates the assignment. The dynamic rubric clearly outlines the assignment's evaluation criteria, and weights assist decide how much each criterion contributes to the overall grade using Foraging Phase Updated Addax Optimization. Subsequently, the assessment score is obtained, and based on this score, feedback generation is performed on the developed model using Generative Attention Long Short Term Memory. Finally, the developed model provides the optimal responses to the students by using the dynamic rubric with a deep learning model and an enhanced optimization algorithm. The experiment scores on two datasets observed over existing models shows average accuracy of 99.36% with 2.7% improvement over K-Means Clustering. Average MAE of 31.85%, reduced by 81% over K-Means. Average Efficiency increase by 21.30% over other models. Thus, the developed model is more effective and robust than the existing approaches.

Cite This Paper

Rudragouda G. Patil, Mahantesh N. Birje, Manisha Tapale, Nagaraj V. Dharwadkar, "AI-Driven Rubrics for Academic Grading & Feedback Using Fuzzy Clustering & Attention Networks", International Journal of Modern Education and Computer Science(IJMECS), Vol.18, No.4, pp. 1-24, 2026. DOI:10.5815/ijmecs.2026.04.01

Reference

[1]M. E. Poehner and . L. Yu, “Dynamic assessment of L2 writing: Exploring the potential of rubrics as mediation in diagnosing learner emerging abilities,” TESOL Quarterly, vol. 56, no. 4, pp. 1191–1217, 2022.
[2]C. Lazou, A. Tsinakos, and I. Kazanidis, “A rubric for peer evaluation of multi-user virtual environments for education and training,” Information, vol. 16, no. 3, p. 174, 2025.
[3]A. Rezai, A. Naserpour, and S. Rahimi, “Online peer-dynamic assessment: An approach to boosting Iranian high school students’ writing skills: A mixed-methods study,” Interactive Learning Environments, vol. 32, no. 1, pp. 306–324, 2024.
[4]M. Chomintra, “Critical race digital literacy rubric for assessing mis/disinformation literacy instruction lesson plans,” The Journal of Academic Librarianship, vol. 50, no. 3, p. 102868, 2024.
[5]L. Zheng, T. Liu, Y. Feng, X. Gu, and. M.-H. Yu, “Dynamic teacher’s technology adoption during the COVID-19 pandemic,” SAGE Open, vol. 14, no. 2, 2024.
[6]B.-J. Boverhof et al., “Radiology AI deployment and assessment rubric (RADAR) to bring value-based AI into radiological practice,” Insights into Imaging, vol. 15, no. 1, p. 34, 2024.
[7]P. Boyd and J. Hill, “Working with rubrics: Codification plus dialogue in developing shared academic standards,” in Academic standards in higher education Routledge, R. Land and J. Gordon, Eds., Routledge, 2024, pp. 169–185.
[8]J. S. Chavis, J. G. Osborn, D. P. Syed, and R. Terrell, “Architecting an enterprise-of-enterprises with the 10-layer rubric: Transforming EoE decision-making,” in 2023 IEEE International Systems Conference (SysCon), IEEE, 2023, pp. 1–8.
[9]A. Fernandez-Sanchez, J. J. Lorenzo-Castineiras, and A. Sanchez-Bello, “Navigating the future of pedagogy: The integration of AI tools in developing educational assessment rubrics,” European Journal of Education, vol. 60, no. 1, p. e12826, 2025.
[10]R. Rockwell, “Navigating transition: Developing an instructional coaching rubric and UDL-infused training for seasoned reading and dyslexia teachers in online education,” International Journal on Studies in Education (IJonSE), vol. 6, no. 3, 2024.
[11]B. D. Garber, “A structured rubric for evaluating the many systemic variables that can contribute to parent–child contact problems (PCCP),” Family Court Review, vol. 62, no. 2, pp. 343–358, 2024.
[12]S. Thite, J. Ravishankar, I. Tomeo-Reyes, and A. M. Ortiz, “Design of a simple rubric to peer-evaluate the teamwork skills of engineering students,” European Journal of Engineering Education, vol. 49, no. 4, pp. 623–646, 2024.
[13]I. Haight, “A rubric for analyzing legal technology using benefit/risk pairs,” University of St. Thomas Law Journal, vol. 20, pp. 107–132, 2024.
[14]Y. R. Kim, J. Yang, Y. Lee, and B. Earwood, “Assessing cybersecurity problem-solving skills and creativity of engineering students through model-eliciting activities using an analytic rubric,” IEEE Access, vol. 12, pp. 5743–5759, 2024.
[15]D. P. Drucker et al., “WorldFAIR (D10.3) agricultural biodiversity FAIR data assessment rubrics [Research report],” 2024.
[16]T. T. Mir, S. A. Khan, and H. Zahra, “Preparing future educators: Assessment literacy and rubric use among prospective teachers,” Journal of Social Sciences Development, vol. 3, no. 3, pp. 179–191, 2024.
[17]A. L. Campbell and P. Padayachee, “Design principles for using rubrics in engineering mathematics,” IEEE Transactions on Education, vol. 67, no. 4, pp. 499–507, 2023.
[18]N. F. Asli, M. E. E. M. Matore, and M. M. Yunus, “Construct validity of primary trait writing rubrics based on assessment use argument (AUA) validation framework,” Heliyon, vol. 10, no. 22, p. e40053, 2024.
[19]J. A. P. Chavira, H. P. Acosta, A. G. Lopez, J. L. Loya, C. R. C. Sanchez, and A. K. N. Acosta, “The socioformative rubrics in the OSCE to assess the level of achievement of the competencies comprising the profile of the physician graduate,” Educacion Medica, vol. 23, no. 3, p. 100740, 2022.
[20]A. Cheung, “Developing and evaluating a set of process and product-oriented classroom assessment rubrics for assessing digital multimodal collaborative writing in L2 classes,” Assessing Writing, vol. 56, p. 100723, 2023.
[21]H. Hashemi, J. Eisner, C. Rosset, B. Van Durme, and C. Kedzie, “LLM-rubric: A multidimensional, calibrated approach to automated evaluation of natural language texts. arXiv,” 2024.
[22]L. D. Bommanaboina and R. D. Bommanaboina, “Enhancing ESL preservice teachers’ formative assessment skills: Developing reflective analytic rubrics for language assessment tasks,” The International Journal of Humanities Education, vol. 23, no. 1, pp. 69–102, 2024.
[23]M. Rahman, M. R. A. Talukder, L. A. Setu, and A. K. Das, “A dynamic strategy for classifying sentiment from Bengali text by utilizing Word2vector model,” Journal of Information Technology Research, vol. 15, pp. 1–17, 2022.
[24]T. Hamadneh et al., “Addax optimization algorithm: A novel nature-inspired optimizer for solving engineering applications,” International Journal of Intelligent Engineering & Systems, vol. 17, no. 3, 2024.
[25]F. Valdez, O. Castillo, and P. Melin, “Bio-inspired algorithms and its applications for optimization in fuzzy clustering,” Algorithms, vol. 14, no. 122, 2021.
[26]Y.-S. Jeong and N.-W. Cho, “Evaluation of e-learners’ concentration using recurrent neural networks,” J Supercomput, vol. 79, no. 4, pp. 4146–4163, Mar. 2023, doi: 10.1007/s11227-022-04804-w.
[27]H. Matsuo et al., “Unsupervised-learning-based method for chest MRI–CT transformation using structure constrained unsupervised generative attention networks,” Scientific Reports, vol. 12, p. 11090, 2022.
[28]A. Meng et al., “Solving large-scale combined heat and power economic dispatch problems by using deep reinforcement learning based crisscross optimization algorithm,” Applied Thermal Engineering, vol. 245, p. 122781, 2024.
[29]T. Hamadneh et al., “Orangutan optimization algorithm: An innovative bio-inspired metaheuristic approach for solving engineering optimization problems,” International Journal of Intelligent Engineering and Systems, vol. 18, pp. 45–58, 2025.
[30]J. Liu, W. Li, and Y. Li, “LWMEO: An efficient equilibrium optimizer for complex functions and engineering design problems,” Expert Systems with Applications, vol. 198, p. 116828, 2022.
[31]A. F. M. Nafuri, N. S. Sani, N. F. A. Zainudin, A. H. A. Rahman, and M. Aliff, “Clustering analysis for classifying student academic performance in higher education,” Applied Sciences, vol. 12, no. 18, p. 9467, 2022.
[32]S. Sarwat et al., “Predicting students’ academic performance with conditional generative adversarial network and deep SVM,” Sensors, vol. 22, no. 13, p. 4834, 2022.
[33]M. J. S. Baron, J. S. G. Sanabria, and J. E. E. Diaz, “Deep neural network (DNN) applied to the analysis of student dropout in a higher education institution,” Investigacion e Innovacion en Ingenierias, vol. 10, pp. 202–214, 2022.
[34]D. Mahajan, et al., “Smart Grading System Using Bi LSTM with Attention Mechanism,” in Advances in Communication and Applications, vol. 1105, N. R. Shetty, N. H. Prasad, and H. C. Nagaraj, Eds., in Lecture Notes in Electrical Engineering, vol. 1105. , Singapore: Springer Nature Singapore, 2024, pp. 247–260. doi: 10.1007/978-981-99-7633-1_18.
[35]H. Liu, “Research on the construction method of curriculum teaching knowledge graph based on Bi-LSTM and CNN algorithm,” International Journal of High Speed Electronics and Systems, vol. 34, 2025.

International Journal of Modern Education and Computer Science (IJMECS)