Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM66535
Volume:
10 |
8 |
Aug 2026
Pages:
1-8
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Faculty of Computing and IT
G M University, Davanagere
Department of Faculty of Computing and IT
G M University, Davanagere
Student feedback plays a decisive role in improving classroom teaching quality, yet most institutions still depend on paper-based or fixed-questionnaire systems that produce only static numerical averages and rarely capture the reasoning behind a rating. This paper presents EduPulse AI, a Smart Faculty Feedback and Teaching Analytics Enterprise Resource Planning (ERP) platform that unifies quantitative rating, free-text feedback and spoken feedback within a single institutional workflow. A faculty member opens a feedback session and generates a session-bound Quick Response (QR) code that a student scans to reach a secure, anonymous feedback form. Feedback may be typed or spoken; spoken responses are converted to text through a speech-to-text module and, together with typed responses, are passed through a Natural Language Processing (NLP) based sentiment and aspect analysis engine that scores feedback on dimensions such as clarity, subject knowledge, punctuality and classroom engagement. Processed results are stored in a relational database and surfaced through role-based dashboards for faculty, heads of department, administrators and parents, along with automatically generated reports. This paper further formalises the scoring process through a mathematical model for aspect-level sentiment, faculty performance and overall rating computation, presents the analysis pipeline as a formal algorithm, and outlines a realistic experimental evaluation plan with target performance metrics. Unlike existing portals that stop at rating aggregation, EduPulse AI closes the loop by returning aspect-level, actionable insight to individual faculty members and department heads. The architecture, module design, data flow, mathematical formulation and entity relationships of the proposed system are described, and its advantages over existing faculty evaluation systems are analysed to establish the practical relevance of the proposed ERP for higher-education institutions.
KEYWORDS
This paper presented EduPulse AI, a Smart Faculty Feedback and Teaching Analytics ERP that integrates session-bound QR-based feedback collection, dual-mode text and voice input, NLP-based sentiment and aspect analysis, and a role-based analytics and reporting layer within a single institutional platform. The literature survey showed that existing faculty evaluation systems either digitise fixed-form collection without analytical depth, apply NLP techniques without institutional integration, or address feedback pedagogy without a supporting technological mechanism. By combining these previously separate capabilities within one ERP data model spanning institution, department, faculty, student and subject entities, and by grounding the scoring process in an explicit mathematical model and algorithm (Sections VI–VII), EduPulse AI is designed to close the loop between feedback collection and actionable, auditable teaching improvement. The proposed architecture, data flow, use cases, entity relationships and planned experimental evaluation establish a practical foundation for implementation, and the identified future directions — including AI-driven chatbots, cloud deployment and predictive analytics — outline a clear path for extending the platform's capability in subsequent phases of development.
[1] A. Kumar and R. Jain, "Faculty evaluation system based on machine learning and natural language processing," 2018. [Journal/conference name, volume, issue and page numbers could not be independently verified and should be confirmed by the authors before submission.] [2] D. Boud and P. Dawson, "What feedback literate teachers do: an empirically-derived competency framework," Assessment & Evaluation in Higher Education, vol. 48, no. 2, pp. 158–171, 2023, doi: 10.1080/02602938.2021.1910928. [3] A. Almubarak, W. Alhalabi, I. Albidewi, and E. Alharbi, "An analytical approach for an AI-based teacher performance evaluation system in Saudi Arabia's schools," Discover Applied Sciences, vol. 6, art. 406, 2024, doi: 10.1007/s42452-024-06117-4. [4] W. Lin, "Design and implementation of an AI-assisted teacher performance evaluation system," in Proc. 2024 3rd Int. Conf. on Artificial Intelligence and Education (ICAIE 2024), Xiamen, China, Nov. 22–24, 2024, pp. 584–589, doi: 10.1145/3722237.3722340. [5] S. Hooda, C. Rana, O. Dahiya, A. Rizwan, and M. S. Hossain, "Artificial intelligence for assessment and feedback to enhance student success in higher education," Mathematical Problems in Engineering, vol. 2022, art. 5215722, pp. 1–19, 2022, doi: 10.1155/2022/5215722. [6] I. Celik, M. Dindar, H. Muukkonen, and S. Järvelä, "The promises and challenges of artificial intelligence for teachers: a systematic review of research," TechTrends, vol. 66, no. 4, pp. 616–630, 2022, doi: 10.1007/s11528-022-00715-y. [7] M. Husain and S. Khan, "Students' feedback: an effective tool in teachers' evaluation system," International Journal of Applied and Basic Medical Research, vol. 6, no. 3, pp. 178–181, Jul.–Sep. 2016, doi: 10.4103/2229-516X.186969. [Note: the journal name has been corrected from "International Journal of Research in Medical Sciences" in the original draft to the verified source, International Journal of Applied and Basic Medical Research.] [8] B. Malecka, D. Boud, and D. Carless, "Eliciting, processing and enacting feedback: mechanisms for embedding student feedback literacy within the curriculum," Teaching in Higher Education, vol. 27, no. 7, pp. 908–922, 2022 (published online 2020), doi: 10.1080/13562517.2020.1754784. [9] M. O. Oloyede, I. A. Sikiru, M. A. Brimmo, N. A. Balogun, and S. A. Sanni, "Development of a web-based feedback system for academic staff assessment," International Journal of Engineering Research & Technology (IJERT), vol. 9, no. 6, Jun. 2020. [Page numbers could not be independently verified and should be confirmed by the authors.] [10] S. A. Dar, "Faculty feedback management system," 2018. [Journal/conference name, volume, issue, page numbers and DOI could not be independently verified and should be confirmed by the authors before submission.]
Publication Date
8/5/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...