English

Improving Customer Service with Automatic Topic Detection in User Emails

Computation and Language 2026-02-19 v3 Artificial Intelligence Machine Learning

Abstract

This study introduces a novel natural language processing pipeline that enhances customer service efficiency at Telekom Srbija, a leading Serbian telecommunications company, through automated email topic detection and labeling. Central to the pipeline is BERTopic, a modular framework that allows unsupervised topic modeling. After a series of preprocessing and postprocessing steps, we assign one of 12 topics and several additional labels to incoming emails, allowing customer service to filter and access them through a custom-made application. While applied to Serbian, the methodology is conceptually language-agnostic and can be readily adapted to other languages, particularly those that are low-resourced and morphologically rich. The system performance was evaluated by assessing the speed and correctness of the automatically assigned topics, with a weighted average processing time of 0.041 seconds per email and a weighted average F1 score of 0.96. The system now operates in the company's production environment, streamlining customer service operations through automated email classification.

Cite

@article{arxiv.2502.19115,
  title  = {Improving Customer Service with Automatic Topic Detection in User Emails},
  author = {Bojana Bašaragin and Darija Medvecki and Gorana Gojić and Milena Oparnica and Dragiša Mišković},
  journal= {arXiv preprint arXiv:2502.19115},
  year   = {2026}
}

Comments

Paper accepted to the 15th International Conference on Information Society and Technology (ICIST), Kopaonik, Serbia, 9-12 March 2025. To appear in L

R2 v1 2026-06-28T21:58:40.018Z