Improving Short Text Classification Robustness to Stochastic Noise Based on Density-Driven Training Data Cleaning
Main Article Content
Abstract
The paper addresses the problem of short text request classification under conditions of significant class imbalance and high noise levels in real-world communication flows. The limited effectiveness of synthetic oversampling techniques when dealing with noisy labeling is demonstrated. A hybrid method is proposed, combining preliminary density-based data cleaning and multi-level model ensembling. The application of a density-based clustering algorithm enabled the exclusion of 16.5% of informational noise from the total sample volume. The final model features a two-level architecture and is optimized using Bayesian hyperparameter search. A Recall@3 (R@3) metric of 97.4% was achieved on a hold-out test set. The proposed method allows for the automation of the request distribution process, significantly reducing operator workload and decreasing dispatch time.
Article Details
References
2. Chawla N.V., Bowyer K.W., Hall L.O., Kegelmeyer W.P. SMOTE: synthetic minority over-sampling technique // Journal of Artificial Intelligence Research. 2002. Vol. 16. P. 321–357. https://doi.org/10.1613/jair.953
3. Zha D. et al. Data-centric Artificial Intelligence: A Survey // ACM Computing Surveys. 2025. Vol. 57, No. 5. Article 129.https://doi.org/10.1145/3711118
4. Salton G., Buckley C. Term-weighting approaches in automatic text retrieval // Information Processing & Management. 1988. Vol. 24, No. 5. P. 513–523. https://doi.org/10.1016/0306-4573(88)90021-0
5. Batiuk T., Dosyn D. Intellectual analysis of textual data in social networks using BERT and XGBOOST // Vìsnik Nacìonalʹnogo Unìversitetu Lʹvìvsʹka Polìtehnìka Serìâ Ìnformacìjnì Sistemi Ta Merežì. 2025. Vol. 17. P. 44–60. https://doi.org/10.23939/sisn2025.17.044
6. Parmar M., Tiwari A. Enhancing text classification performance using stacking ensemble method with TF-IDF feature extraction // Proceedings of the 5th International Conference on Mobile Computing and Sustainable Informatics (ICMCSI). Kathmandu, Nepal. 2024. P. 166–174. https://doi.org/10.1109/ICMCSI61480.2024.10493890
7. Zemp M. Text classification of service desk tickets. Master's thesis. Winterthur, Zurich University of Applied Sciences. 2021. https://www.zhaw.ch/storage/shared/upload/MAS21_Ticket_Classification_Zemp.pdf
8. Akhbardeh F., Alm C.O., Zampieri M., Desell T. Handling extreme class imbalance in technical logbook datasets // Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP). Online. 2021. P. 4034–4045. https://doi.org/10.18653/v1/2021.acl-long.312
9. Padurariu C., Breaban M.E. Dealing with data imbalance in text classification // Procedia Computer Science. 2019. Vol. 159. P. 736–745. https://doi.org/10.1016/j.procs.2019.09.229
10. Asyaky M.S., Mandala R. Improving the performance of HDBSCAN on short text clustering by using word embedding and UMAP // 2021 8th International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA). Bandung, Indonesia. 2021. P. 1–6. https://doi.org/10.1109/ICAICTA53211.2021.9640285
11. McInnes L., Healy J., Astels S. hdbscan: Hierarchical density based clustering // Journal of Open Source Software. 2017. Vol. 2, No. 11. P. 205. https://doi.org/10.21105/joss.00205
12. Khalov A.P., Ataeva O.M. Automatic and semi-automatic methods for constructing a domain knowledge graph and ontology expansion // Russian Digital Libraries Journal. 2025. Vol. 28, No. 6. P. 1481–1519 (in Russian). https://doi.org/10.26907/1562-5419-2025-28-6-1481-1519
13. Wolpert D.H. Stacked generalization // Neural Networks. 1992. Vol. 5, No. 2. P. 241–259. https://doi.org/10.1016/S0893-6080(05)80023-1
14. Charikar M.S. Similarity estimation techniques from rounding algorithms // Proceedings of the thirtieth annual ACM symposium on Theory of computing (STOC). 2002. P. 380–388. https://doi.org/10.1145/509907.509965
15. Micci-Barreca D. A preprocessing scheme for high-cardinality categorical attributes in classification and prediction problems // SIGKDD Explorations Newsletter. 2001. Vol. 3, No. 1. P. 27–32. https://doi.org/10.1145/507533.507538
16. Chen T., Guestrin C. XGBoost: A scalable tree boosting system // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). San Francisco, USA. 2016. P. 785–794. https://doi.org/10.1145/2939672.2939785
17. Akiba T., Sano S., Yanase T., Ohta T., Koyama M. Optuna: A next-generation hyperparameter optimization framework // Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD). Anchorage, USA. 2019. P. 2623–2631. https://doi.org/10.1145/3292500.3330701
This work is licensed under a Creative Commons Attribution 4.0 International License.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.