AI-Driven Hierarchical Taxonomy Generation from Emergency Call Transcripts

Juan Gabriel Flores Sanchez; Marcos Orellana; Patricio Santiago García-Montero; Jorge Luis Zambrano-Martinez

doi:10.5753/jbcs.2026.6635

Authors

Juan Gabriel Flores Sanchez Computer Science Research & Development Laboratory (LIDI), Universidad del Azuay, Cuenca - Ecuador https://orcid.org/0000-0002-1249-2255
Marcos Orellana Computer Science Research & Development Laboratory (LIDI), Universidad del Azuay, Cuenca - Ecuador https://orcid.org/0000-0002-3671-9362
Patricio Santiago García-Montero Computer Science Research & Development Laboratory (LIDI), Universidad del Azuay, Cuenca - Ecuador https://orcid.org/0009-0007-4113-8400
Jorge Luis Zambrano-Martinez Computer Science Research & Development Laboratory (LIDI), Universidad del Azuay, Cuenca - Ecuador https://orcid.org/0000-0002-5339-7860

DOI:

https://doi.org/10.5753/jbcs.2026.6635

Keywords:

Hierarchical Text Classification, Emergency Call Analysis, BERTopic, Large Language Models, Natural Language Processing, Multilingual NLP, Emergency Communication Systems

Abstract

This article presents a case study on hierarchical topic modeling for emergency call transcripts from Ecuador's ECU 911 service. We introduce a hybrid methodology that first generates a taxonomy from unlabeled data using BERTopic and agglomerative clustering, and then employs embedding-based similarity for multi-label classification. By leveraging multilingual embeddings (LaBSE) and clustering algorithms (UMAP & HDBSCAN), we identified 23 coherent topics, demonstrating a practical balance between accuracy and operational applicability. The key result is a significant reduction in Hamming Loss and an F1-score of 0.4951, achieved without the need for pre-labeled data. This underscores the method's primary practical significance: offering a scalable, automated solution for emergency management centers to rapidly categorize complex incidents, thereby enhancing situational awareness and resource allocation. The integration of LLaMA 3 for automated label generation further optimized semantic interpretation, highlighting the potential of language models in critical, resource-constrained domains.

Downloads

Download data is not yet available.

Author Biography

Jorge Luis Zambrano-Martinez, Computer Science Research & Development Laboratory (LIDI), Universidad del Azuay, Cuenca - Ecuador

Jorge Luis Zambrano-Martinez is a Ph.D. in Computer Science received in Department of Networking Research Group (GRC) at the Universitat Politècnica de València (UPV) from Spain in 2019, included an awarded international doctoral and an awarded Cum Laude. He graduated in Master's Degree in Information and Communication Technology Security at Universitat Oberta de Catalunya in 2018. He graduated in Master’s Degree in Computer Engineering at Universitat Politècnica de València (UPV) in 2015. He graduated in Systems Engineering at Polytechnic University Salesian (Ecuador) in 2011. His research interests include Vehicular Networks, Smart Cities & IoT, Network Security, ITS, and Computer Vision.

References

Andirov, M., Assan, Z. Z., Nopembri, S., Seilkhan, A., and Myrzakhmetov, D. (2023). Classification of texts on emergency situations in almaty. Kompleksnoe Ispolzovanie Mineralnogo Syra= Complex use of mineral resources, 327(4):23-31. DOI: 10.31643/2023/6445.36.

Egger, R. and Yu, J. (2022). A topic modeling comparison between lda, nmf, top2vec, and bertopic to demystify twitter posts. Frontiers in sociology, 7:886498. DOI: 10.3389/fsoc.2022.886498.

Gargiulo, F., Silvestri, S., Ciampi, M., and De Pietro, G. (2019). Deep neural network for hierarchical extreme multi-label text classification. Applied Soft Computing, 79:125-138. DOI: 10.1016/j.asoc.2019.03.041.

Haj-Yahia, Z., Sieg, A., and Deleris, L. A. (2019). Towards unsupervised text classification leveraging experts and word embeddings. In Proceedings of the 57th annual meeting of the Association for Computational Linguistics, pages 371-379. DOI: 10.18653/v1/P19-1036.

Jiang, T., Wang, D., Sun, L., Chen, Z., Zhuang, F., and Yang, Q. (2022). Exploiting global and local hierarchies for hierarchical text classification. arXiv preprint arXiv:2205.02613. DOI: 10.48550/arXiv.2205.02613.

Kowsari, K., Jafari Meimandi, K., Heidarysafa, M., Mendu, S., Barnes, L., and Brown, D. (2019). Text classification algorithms: A survey. Information, 10(4):150. DOI: 10.3390/info10040150.

Li, Q., Peng, H., Li, J., Xia, C., Yang, R., Sun, L., Yu, P. S., and He, L. (2022). A survey on text classification: From traditional to deep learning. ACM Transactions on Intelligent Systems and Technology (TIST), 13(2):1-41. DOI: 10.1145/3495162.

Li, Z., Zhu, H., Lu, Z., and Yin, M. (2023). Synthetic data generation with large language models for text classification: Potential and limitations. arXiv preprint arXiv:2310.07849. DOI: 10.18653/v1/2023.emnlp-main.647.

Liu, Y. and Wan, F. (2024). Unveiling temporal and spatial research trends in precision agriculture: A bertopic text mining approach. Heliyon. DOI: 10.1016/j.heliyon.2024.e36808.

Malzer, C. and Baum, M. (2020). A hybrid approach to hierarchical density-based cluster selection. In 2020 IEEE international conference on multisensor fusion and integration for intelligent systems (MFI), pages 223-228. IEEE. DOI: 10.1109/MFI49285.2020.9235263.

McInnes, L., Healy, J., and Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426. DOI: 10.48550/arXiv.1802.03426.

Orellana, M., Molina Pinos, P. A., García-Montero, P. S., and Zambrano-Martinez, J. L. (2024). Pre-processing of the text of ecu 911 emergency calls. In Conference on Information and Communication Technologies of Ecuador, pages 271-284. Springer. DOI: 10.1007/978-3-031-75431-9_18.

Pacheco, S. A. d. J. S., Romero, F. C., Domíınguez, R. G., and Vasconcelos, M. P. (2023). Clasificación jerárquica de texto con machine learning en la industria petrolera. Innovación y Desarrollo Tecnológico. Available at:[link].

Palanivinayagam, A., El-Bayeh, C. Z., and Damaševičius, R. (2023). Twenty years of machine-learning-based text classification: A systematic review. Algorithms, 16(5):236. DOI: 10.3390/a16050236.

Rosner, F., Hinneburg, A., Röder, M., Nettling, M., and Both, A. (2014). Evaluating topic coherence measures. arXiv preprint arXiv:1403.6397. DOI: 10.48550/arXiv.1403.6397.

Stammbach, D. and Ash, E. (2021). Docscan: Unsupervised text classification via learning from neighbors. arXiv preprint arXiv:2105.04024. DOI: 10.48550/arXiv.2105.04024.

Tang, Z., Pan, X., and Gu, Z. (2024). Analyzing public demands on china’s online government inquiry platform: A bertopic-based topic modeling study. Plos one, 19(2):e0296855. DOI: 10.1371/journal.pone.0296855.

Topal, M. O., Bas, A., and van Heerden, I. (2021). Exploring transformers in natural language generation: Gpt, bert, and xlnet. arXiv preprint arXiv:2102.08036. DOI: 10.48550/arXiv.2102.08036.

Wang, Z., Wang, L., Huang, C., Sun, S., and Luo, X. (2023). Bert-based chinese text classification for emergency management with a novel loss function. Applied Intelligence, 53(9):10417-10428. DOI: 10.1007/s10489-022-03946-x.

Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., and Zhang, Y. (2024). A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. High-Confidence Computing, page 100211. DOI: 10.1016/j.hcc.2024.100211.

Yuan, S. and Wang, Q. (2022). Imbalanced traffic accident text classification based on bert-rcnn. In Journal of Physics: Conference Series, number 1 in 2170, page 012003. IOP Publishing. DOI: 10.1088/1742-6596/2170/1/012003.

Zhang, Y., Yang, R., Xu, X., Li, R., Xiao, J., Shen, J., and Han, J. (2025). Teleclass: Taxonomy enrichment and llm-enhanced hierarchical text classification with minimal supervision. In Proceedings of the ACM on Web Conference 2025, pages 2032-2042. DOI: 10.1145/3696410.3714940.

Zhou, J., Ma, C., Long, D., Xu, G., Ding, N., Zhang, H., Xie, P., and Liu, G. (2020). Hierarchy-aware global model for hierarchical text classification. In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 1106-1117. DOI: 10.18653/v1/2020.acl-main.104.