Addressing Postgraduate Supervision Bottlenecks Through Automated Structural and Formatting Feedback for Research Proposals

Opeoluwa Iwashokun; Abejide Ade-Ibijola

doi:10.53941/bci.2026.100007

Abstract

Arguably, the role of a postgraduate supervisor is aligned to support the student to think critically and be able to write academically, but not necessarily as a “proofreader” for checking spelling, grammar, or syntax inconsistencies. This process can be realised as an AI-based tool providing near–real-time automated feedback to students, whilst reducing academic workload pressures. This paper proposes a formal (referring to rules) based proofreading process for information extraction, recognition, and correction of meaningful text chunks, images or figures, and tables (referred to as document tokens) from research proposals. The ultimate objective is custom-fit automated generation of feedback across multiple sections of submitted research proposals for a large number of authors. To this effect, an AI-driven tool was developed to support the proofreading of research proposals by delivering timely, automated feedback at scale, named RX Autoproofreader. The tool’s test on eighty (80) publicly available research documents analysed for constituent parts recognition and proofreading in an algorithm programmed in a c# Visual Studio environment, which ran in 182 min, produced an average accuracy of 68%. During the test, the tool extracted and proofread a total of 14,231 document pages into meaningful items of title, author, supervisor, research date, aim, objectives, figures, tables, paragraphs, lists, headings, and page numbers. The recognition and extraction of unstructured texts into meaningful items is a document understanding task necessary for proofreading and feedback generation. It aims to complement existing spell and grammar tools for proofreading academic manuscripts.

References

1.
Huang, Z.; teWinkel, W. Automated feedback: An AI-powered tool to scale microlevel feedback for better academic writing. In Proceedings of EUNIS 2022 Annual Congress: Good for All in the Digital World, G¨ottingen, Germany, 1–3 June 2022.
2.
Yeung, S. A comparative study of rule-based, machine learning and large language model approaches in automated writing evaluation (AWE). In Proceedings of the 15th International Learning Analytics and Knowledge Conference, Dublin, Ireland, 3–7 March 2025; pp. 984–991.
3.
van Rensburg, G.; Mayers, P.; Roets, L. Supervision of post-graduate students in higher education. Trends Nurs. 2016, 3. https://doi.org/10.14804/3-1-55.
4.
Abel, S. Towards Automated Feedback on Students’ Research Writing: Theory, Design and Evaluation. PhD Thesis, University of Technology Sydney, Ultimo, Australia, 2022.
5.
Iwashokun, O.; Ade-Ibijola, A. Structural vetting of academic proposals. Int. J. Adv. Comput. Sci. Appl. 2022, 13, 772–782.
6.
Saeed, M.A.; Qunayeer, H.S.A.; AL-Jaberi, M.A. Exploring Supervisory Feedback Formulation on Academic Writing of Research Proposals and Postgraduates’ Responses to Feedback: A Case Study. SAGE Open 2021, 11. https://doi.org/10.1177/21582440211007125.
7.
Qinjin, J.; Mitchell, Y.; Yunkai, X.; et al. Automated Feedback Generation for Student Project Reports: A Data-Driven Approach. J. Educ. Data Min. 2022, 14, 132–161.
8.
Keuning, H.; Jeuring, J.; Heeren, B. A Systematic Literature Review of Automated Feedback Generation for Programming Exercises. Acm Trans. Comput. Educ. 2018, 19, 1–43.
9.
Pinheiro, A.; Barbosa, A.; Carvalho, R.; et al. Automatic feedback in online learning environments: A systematic literature review. Comput. Educ. Artif. Intell. 2021, 2, 100027.
10.
Hawari, O.M.A.; Al-Shboul, Y.; Huwari, I.F. Supervisors’ Perspectives on Graduate Students’ Problems in Academic Writing. Eur. J. Educ. Res. 2022, 11, 545–556.
11.
Calma, A.; Cotronei-Baird, V.; Chia, A. Grammarly: An instructional intervention for writing enhancement in management education. Int. J. Manag. Educ. 2022, 20, 100704.
12.
Jalal, S.K.; Sutradhar, B. Subscription, Access and Licensing Issues of E-resources. Pearl J. Libr. Inf. Sci. 2020, 14, 7–14.
13.
Bastola, M.N. Engagement and Challenges in Supervisory Feedback: Supervisors’ and Students’ Perceptions. RELC J. 2022, 53, 56–70.
14.
Oke, A.; Fernandes, F.A.P. Innovations in Teaching and Learning: Exploring the Perceptions of the Education Sector on the 4th Industrial Revolution (4IR). J. Open Innov. Technol. Mark. Complex. 2020, 6, 31.
15.
Yende, S.J. A Transition towards the Fourth Industrial Revolution (4IR) in the South African Education Sector: A Perspective from Rural-based Higher Education. Afr. J. Dev. Stud. 2021, 11, 55–75. https://hdl.handle.net/10520/ejcaaaffrika1 v11 n2 a3.
16.
Grajek, S. Top 10 IT Issues, 2022: The Higher Education We Deserve. Available online: https://er.educause.edu/articles/2021/11/top-10-it-issues-2022-the-higher-education-we-deserve (accessed on 8 June 2022).
17.
Deeva, G.; Bogdanova, D.; Serral, E.; et al. A review of automated feedback systems for learners: Classification framework, challenges and opportunities. Comput. Educ. 2021, 162, 104094.
18.
Strobl, C.; Ailhaud, E.; Benetos, K.; et al. Digital support for academic writing: A review of technologies and pedagogies. Comput. Educ. 2019, 131, 33–48.
19.
Lee, A.V.Y.; Luco, A.C.; Tan, S.C. A human-centric automated essay scoring and feedback system for the development of ethical reasoning. Educ. Technol. Soc. 2023, 26, 147–159.
20.
Vashishth, T.K.; Sharma, V.; Sharma, K.K.; et al. AI-driven learning analytics for personalized feedback and assessment in higher education. In Using Traditional Design Methods to Enhance AI-Driven Decision Making; IGI Global Scientific Publishing: Hershey, PA, USA, 2024; pp. 206–230.
21.
Khasawneh, D. Improving the learning of language proficiency at tertiary education level through AI-driven assessment models and automated feedback systems. Migr. Lett. 2024, 21, 712–726.
22.
Larrondo, P.; Frank, B.; Ortiz, J. The State of the Art in Providing Automated Feedback to Open-Ended Student Work. Proceedings of the Canadian Engineering Education Association (CEEA), Virtual, 20–23 June 2021.
23.
Kubeka, S.; Ade-ibijola, A. Automatic Comprehension and Summarisation of Legal Contracts. Adv. Sci. Technol. Eng. Syst. J. 2021, 6, 19–28.
24.
Abbott, S.; Ade-Ibijola, A. Algorithms and a Tool for Automatic Decryption of Clinical Notes. In Proceedings of the 6th International Conference on Soft Computing & Machine Intelligence (ISCMI), Johannesburg, South Africa, 19–20 November 2019; pp. 137–143.
25.
Zhou, Y.C.; Zheng, Z.; Lin, J.R.; et al. Integrating NLP and context-free grammar for complex rule interpretation towards automated compliance checking. Comput. Ind. 2022, 142, 103746.
26.
Jackson, D.; Power, T.; Usher, K. Feedback as a balancing act: Qualitative insights from an experienced multi-cultural sample of doctoral supervisors in nursing. Nurse Educ. Pract. 2021, 54, 103125.
27.
Hao, Q.; Smith IV, D.H.; Ding, L.; et al. Towards understanding the effective design of automated formative feedback for programming assignments. Comput. Sci. Educ. 2022, 32, 105–127.
28.
Tas, B.; Aksoy, M. GPT as a Reviewer: Automatic Evaluation of Academic Papers. In Proceedings of the 11th International Conference on Computing and Artificial Intelligence (ICCAI), Kyoto, Japan, 28–31 March 2025; pp. 487–496.
29.
Algburi, E.; Razali, A.B.; Nimehchisalem, V.; et al. Combination of AWE (Criterion) Feedback with the Process Approach and Its Impact on EFL Writing Content/Idea Development and Organization. Int. J. Acad. Res. Progress. Educ. Dev. 2024, 13, 793–803.

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us