Natural Language Processing and Machine Learning in news categorization
DOI:
https://doi.org/10.29352/mill0223e.47447Keywords:
natural language processing; machine learning; text classification; news categorization; BERT; artificial intelligenceAbstract
Introduction: The rapid growth of digital content, especially in the news domain, has made more difficult to organize and analyze large volumes of unstructured information. Automatic text classification is an important solution, supported by advances in Natural Language Processing and Machine Learning, which make news categorization more efficient and accurate.
Objective: To develop and evaluate methods for automatic categorization of news in Portuguese that combine strong performance with computational efficiency, comparing traditional techniques with advanced deep learning models.
Methods: An experimental study was conducted, based on literature review, exploratory data analysis, and the implementation of different classification models. Classical Machine Learning and Text Mining approaches were compared with recent Natural Language Processing models, including Transformer-based architectures such as BERT. The evaluation was carried out using performance metrics (Accuracy, Precision, Recall, F1-Score) and computational cost.
Results: Transformer-based models demonstrated greater contextual understanding and superior performance in news classification. However, they require higher computational resources. In contrast, lighter models showed a better balance between efficiency and accuracy, proving suitable for scenarios with limited computational resources.
Conclusion: Effective solutions for automatic news categorization in Portuguese can balance performance and computational efficiency. The study highlights the importance of selecting the appropriate model for the context, supporting the development of more robust and accessible classification systems.
Downloads
References
Aggarwal, C. C. (2018). Machine learning for text. Springer International Publishing. https://doi.org/10.1007/978-3-319-73531-3
Chitty-Venkata, K. T., Emani, M., Vishwanath, V., & Somani, A. K. (2022). Neural architecture search for transformers: A survey. IEEE access, 10, 108374-108412. https://doi.org/10.1109/ACCESS.2022.3212767
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT) (pp. 4171–4186). https://doi.org/10.18653/v1/N19-1423
Gupta, R., Shenoy, S. & Mahajan, S. (2024) Analysis and comparison of dimensionality reduction techniques for news blog classification. In 2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES). IEEE. https://doi.org/10.1109/ICSES63760.2024.10910686
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Jurafsky, D., & Martin, J. H. (2026). Speech and Language Processing: An introduction to natural language processing, computational linguistics, and speech recognition with language models, (3rd ed.). Online manuscript. https://web.stanford.edu/~jurafsky/slp3
Lauriola, I., Lavelli, A., & Aiolli, F. (2022). An introduction to deep learning in natural language processing: Models, techniques, and tools. Neurocomputing, 470, 443-456. https://doi.org/10.1016/j.neucom.2021.05.103
Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to information retrieval. Cambridge University Press. https://doi.org/10.1017/CBO9780511809071
Rezaeenour, J., Ahmadi, M., Jelodar, H., & Shahrooei, R. (2023). Systematic review of content analysis algorithms based on deep neural networks. Multimedia Tools and Applications, 82(12), 17879-17903. https://doi.org/10.1007/s11042-022-14043-z
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2020). DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter. arXiv. https://doi.org/10.48550/arXiv.1910.01108
Sarikaya, R., et al. (2024). Deep learning architectures for NLP applications. ACM Computing Surveys, 56(2), 1–34. https://doi.org/10.13140/RG.2.2.18207.83368
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002
Sun, G., Cheng, Y., Zhang, Z., Tong, X., & Chai, T. (2024). Text classification with improved word embedding and adaptive segmentation. Expert Systems with Applications, 238, 121852. https://doi.org/10.1016/j.eswa.2023.121852
Taha, K., Yoo, P. D., Yeun, C., Homouz, D., & Taha, A. (2024). A comprehensive survey of text classification techniques and their research applications: Observational and experimental insights. Computer Science Review, 54, 100664. https://doi.org/10.1016/j.cosrev.2024.100664
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS), 30.
https://doi.org/10.48550/arXiv.1706.03762
Zhang, Y., & Wallace, B. (2017). A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification. arXiv. https://doi.org/10.48550/arXiv.1510.03820
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Millenium - Journal of Education, Technologies, and Health
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who submit proposals for this journal agree to the following terms:
a) Articles are published under the Licença Creative Commons (CC BY 4.0), in full open-access, without any cost or fees of any kind to the author or the reader;
b) The authors retain copyright and grant the journal right of first publication, allowing the free sharing of work, provided it is correctly attributed the authorship and initial publication in this journal;
c) The authors are permitted to take on additional contracts separately for non-exclusive distribution of the version of the work published in this journal (eg, post it to an institutional repository or as a book), with an acknowledgment of its initial publication in this journal;
d) Authors are permitted and encouraged to publish and distribute their work online (eg, in institutional repositories or on their website) as it can lead to productive exchanges, as well as increase the impact and citation of published work
Documents required for submission
Article template (Editable format)
