Towards Improving Teacher Performance Assessment through Human-Centered AI-Powered Survey Analysis
An Approach Using Large Language Models (LLM)
DOI:
https://doi.org/10.47756/aihc.y9i1.181Keywords:
Machine Learning, Large Language Models, Artificial Intelligence, Survey analysis, Text AnalysisAbstract
Practical evaluation is crucial for improving educational quality. The blind review conducts semester surveys among students at all academic levels within the institution for a comprehensive professor performance assessment. However, processing this data manually is time-consuming and restricts in-depth analysis. With the recent advancements in Large Language Models, such as OpenAI's GPT-4, chatbots can now accurately interpret nuanced survey responses. We propose using a chatbot powered by artificial intelligence and natural language processing, specifically large language models, to streamline survey analysis. This technology aims to quickly extract important insights, reduce staff workload, and enable informed decision-making. We are utilizing user-centered design methods to create and assess a prototype, ensuring that it meets the specific needs and characteristics of the users and provides an optimal user experience in the final product. This implementation will significantly improve operational efficiency and support continuous educational enhancement at the institution.
Downloads
References
A. Tersoo Catherine, S. K. Towfek, y A. A. Abdelhamid, “An Overview of the Evolution and Impact of Chatbots in Modern Healthcare Services”, MJAIH, vol. 2023, pp. 71–75, dic. 2023, doi: 10.58496/MJAIH/2023/014. DOI: https://doi.org/10.58496/MJAIH/2023/014
M. Mbaye, “Impact of Artificial Intelligence (AI) on the E-Commerce Business: Empirical Analysis for Optimal Use of the Chatbot”, vol. 30, núm. 2, 2024.
C. Bjelland, K. Ludvigsen, y A. Møgelvang, “Unveiling the Impact of AI Chatbots on Higher Education: Insights from Students”, presentado en 18th INTED, mar. 2024, pp. 1458–1465. doi: 10.21125/inted.2024.0428. DOI: https://doi.org/10.21125/inted.2024.0428
A. Rossmann, A. Zimmermann, y D. Hertweck, “The Impact of Chatbots on Customer Service Performance”, en Advances in the Human Side of Service Engineering, vol. 1208, J. Spohrer y C. Leitner, Eds., en Advances in Intelligent Systems and Computing, vol. 1208. , Cham: Springer International Publishing, 2020, pp. 237–243. doi: 10.1007/978-3-030-51057-2_33. DOI: https://doi.org/10.1007/978-3-030-51057-2_33
L. Grebennikov y M. Shah, “Student voice: using qualitative feedback from students to enhance their university experience”, Teaching in Higher Education, vol. 18, núm. 6, pp. 606–618, ago. 2013, doi: 10.1080/13562517.2013.774353. DOI: https://doi.org/10.1080/13562517.2013.774353
B. J. Jansen, S. Jung, y J. Salminen, “Employing large language models in survey research”, Natural Language Processing Journal, vol. 4, p. 100020, sep. 2023, doi: 10.1016/j.nlp.2023.100020. DOI: https://doi.org/10.1016/j.nlp.2023.100020
Z. Wang, P. Denny, J. Leinonen, y A. Luxton-Reilly, “Leveraging Large Language Models for Analysis of Student Course Feedback”, en Proceedings of the 16th Annual ACM India Compute Conference, Hyderabad India: ACM, dic. 2023, pp. 76–79. doi: 10.1145/3627217.3627221. DOI: https://doi.org/10.1145/3627217.3627221
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
AMexIHC make every effort to ensure the accuracy and rigour of all the information (the "Content") contained in out publications. However, AMexIHC and our representatives make no representations or warranties whatsoever as to the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by AMexIHC. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information.
