Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/148245
Title: Evaluation of agreement-related e-mail classification models with unbalanced classes
Authors: Hernes, Marcin
Rot, Artur
Walaszczyk, Ewa
Tyburcy, Janusz
Hańczyk, Abigail
Keywords: Machine learning
Electronic mail systems
Commercial correspondence
Expert systems (Computer science)
Issue Date: 2026
Publisher: University of Piraeus. International Strategic Management Association
Citation: Hernes, M., Rot, A., Walaszczyk, E., Tyburcy, J., & Hańczyk, A. (2026). Evaluation of agreement-related e-mail classification models with unbalanced classes. European Research Studies Journal, 29(2), 345-356.
Abstract: PURPOSE: The aim of the research is to evaluate the effectiveness of classification models of agreement-related emails with imbalanced classes, which allows for a more comprehensive assessment of their performance under severely imbalanced data and a better understanding of their behaviour in practical applications.
DESIGN/METHODOLOGY/APPROACH: The following machine learning classification methods have been used: Complement Naive Bayes, Logistic Regression, Random Forest, and Support Vector Machine.
FINDINGS: This research evaluated the effectiveness of classification models for agreementrelated emails with imbalanced classes. Random Forest and Support Vector Machine achieve high values for both Accuracy and balanced Accuracy, demonstrating their strong classification performance.
PRACTICAL IMPLICATIONS: Random Forest and Support Vector Machine can be implemented in intelligent information systems for a mail dispatcher. Correspondence can be automatically routed to the person responsible for handling the inquiry. This speeds up the process and minimises the risk of an inquiry being overlooked or left unanswered.
ORIGINALITY/VALUE: Despite a large body of research on email classification, there is still a lack of studies focused on specific applications, such as agreement document classification. In particular, it is rare to simultaneously examine different models and compare their performance using multiple metrics within a single real-world problem.
URI: https://www.um.edu.mt/library/oar/handle/123456789/148245
Appears in Collections:European Research Studies Journal, Volume 29, Issue 2

Files in This Item:
File Description SizeFormat 
ERSJ29(2)A20.pdf429.46 kBAdobe PDFView/Open


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.