Automated University Complaint Management System by Leveraging Machine Learning and Natural Language Processing for Enhanced Efficiency and Accuracy

Authors

  • Hanad Mohamud Mohamed

    Faculty of Computer & IT, Jamhuriya University of Science and Technology, Mogadishu, Somalia
  • Abdishakur Hassan Mohamed

    Faculty of Computer & IT, Jamhuriya University of Science and Technology, Mogadishu, Somalia
  • Sabrin Omar Hashi

    Faculty of Computer & IT, Jamhuriya University of Science and Technology, Mogadishu, Somalia
  • Hassan Nur Hassan

    Faculty of Computer & IT, Jamhuriya University of Science and Technology, Mogadishu, Somalia
  • Khadar Abdirahman Barre

    Faculty of Computer & IT, Jamhuriya University of Science and Technology, Mogadishu, Somalia
  • Bashir Abdinur Ahmed

    Faculty of Computer & IT, Jamhuriya University of Science and Technology, Mogadishu, Somalia

DOI:

https://doi.org/10.30564/fls.v7i2.8162
Received: 6 December 2024 | Revised: 12 January 2025 | Accepted: 13 January 2025 | Published Online: 5 February 2025

Abstract

The goal of this research is to create an automated system that works with machine learning (ML) and natural language processing (NLP) to automate university complaint management. Students get dissatisfied when traditional complaint handling techniques, such physical suggestion boxes, are ineffective and prone to delays. Designing and implementing a system that automates the submission, classification, and analysis of student complaints especially those made in Somali is the aim of this project. The suggested approach greatly lessens the manual workload of university administrators by classifying issues into Academic, Finance, and Equipment using a machine learning model trained on complaint data. The system has an administrative dashboard for tracking and handling complaints, as well as an easy-to-use interface for filing complaints. The primary results show that the system improves the accuracy and efficiency of resolving complaints, which results in quicker resolution times and pleased students. Proactive decision-making is made possible by the system’s integration of data analytics, which also offers insightful information on persistent problems. According to the project’s findings, automated complaint handling can greatly enhance the entire university experience by creating a more accommodating and student-focused atmosphere. 

Keywords:

Automated Complaint Management; Machine Learning; Natural Language Processing; University Administration; Student Satisfaction

References

[1] Hossen, M.S., Chowdhury, M.N.A., Sristy, A.M., et al., 2022. Sentiment analysis using machine learning and NLP for digital education. In Proceedings of the 6th International Conference on Computational Methodologies and Communications (ICCMC 2022); Erode, India; 29–31 March 2022. pp. 902–908. DOI: https://doi.org/10.1109/ICCMC53470.2022.9754065

[2] Hassan, M.A., Hassan, Z.A., Ali, A.S., et al., 2024. Predicting customer churn in telecommunication companies in Somalia using machine learning. Proceedings of the 2024 1st International Conference on Emerging Technologies for Dependable Internet of Things (ICETI); Sana'a, Yemen; 25–26 November 2024. IEEE. pp. 1–9. DOI: https://doi.org/10.1109/ICETI63946.2024.10777125

[3] Pham, T.D., Vo, D., Li, F., et al., 2020. Natural language processing for analysis of student online sentiment in a postgraduate program. Pacific Journal of Technology Enhanced Learning. 2(2), 15–30. DOI: https://doi.org/10.24135/pjtel.v2i2.4

[4] Tyagi, P., 2020. Sentiment analysis of restaurant reviews. Journal of Natural Language Processing. 7(7).

[5] Manuhutu, M.A., Uktolseja, L.J., 2018. Design and implementation of online students' complaint (case study of English Study Program at Victory University, Sorong). International Journal of Computer Science and Engineering. 6(1), 228–232.

[6] Nandwani, P., 2021. A review on sentiment analysis and emotion detection from text. Social Network Analysis and Mining. 11(81). DOI: https://doi.org/10.1007/s13278-021-00776-6

[7] Bergman, S., Humble, N., 2022. Sentiment analysis for emotional navigation in written communication: What support do autistic people need? In: European Conference on the Impact of Artificial Intelligence and Robotics. Volume 4, No. 1, pp. 6–11.

[8] El Ansari, W., Oskrochi, R., Haghgoo, G., 2014. Are students' symptoms and health complaints associated with perceived stress at university? Perspectives from the United Kingdom and Egypt. International Journal of Environmental Research and Public Health. 11(10), 9981–10002. DOI: https://doi.org/10.3390/ijerph111009981

[9] Hart, D., Coates, N., 2011. International student complaint behaviour: Understanding how East-Asian business and management students respond to dissatisfaction during their university experience. International Journal of Management Education. 9(4), 57–66. DOI: https://doi.org/10.3794/ijme.94.380

[10] Caldeira, L.N., Ribeiro, R., 2022. Classification of public administration complaints. OpenAccess Series in Informatics. 104(9), 9:1–9:12. DOI: https://doi.org/10.4230/OASIcs.SLATE.2022.9

[11] Cranfield, D.J., Tick, A., Venter, I.M., et al., 2021. Higher education students' perceptions of online learning during COVID-19—A comparative study. Education Sciences. 11(8), 403. DOI: https://doi.org/10.3390/educsci11080403

[12] Dang, N.C., Moreno-García, M.N., De la Prieta, F., 2020. Sentiment analysis based on deep learning: A comparative study. Electronics. 9(3), 483. DOI: https://doi.org/10.3390/electronics9030483

[13] Al-Momani, K.R., 2014. Strategies of persuasion in letters of complaint in academic context: The case of Jordanian university students' complaints. Discourse Studies. 16(2), 1–24. DOI: https://doi.org/10.1177/1461445614546257

[14] Onan, A., 2020. Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks. Concurrency and Computation: Practice and Experience. 33(23), e5909. DOI: https://doi.org/10.1002/cpe.5909

[15] Yadav, A., Vishwakarma, D.K., 2020. Sentiment analysis using deep learning architectures: A review. Artificial Intelligence Review. 53, 4335–4385. DOI: https://doi.org/10.1007/s10462-019-09794-5

[16] Jimale, M.A., Ali, M.A., Ahmed, B.A., et al., 2024. Comprehensive ATM security framework combining GSM alert messaging and GPS location tracking. Smart applications and sustainability in the AIoT era. In: SAS-AIoT 2024. Sustainable civil infrastructures. Springer: Cham, Switzerland. Volume 86, pp. 896–907. DOI: https://doi.org/10.1007/978-3-031-78276-3_86

Downloads

How to Cite

Mohamed, H. M., Mohamed, A. H., Hashi, S. O., Hassan, H. N., Barre, K. A., & Ahmed, B. A. (2025). Automated University Complaint Management System by Leveraging Machine Learning and Natural Language Processing for Enhanced Efficiency and Accuracy. Forum for Linguistic Studies, 7(2), 373–354. https://doi.org/10.30564/fls.v7i2.8162

Issue

Vol. 7 , Iss. 2 (February 2025): In Progress

Article Type

Article

License

Copyright © 2025 Hanad Mohamud Mohamed, Abdishakur Hassan Mohamed, Sabrin Omar Hashi, Hassan Nur Hassan, Khadar Abdirahman Barre, Bashir Abdinur Ahmed

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.