TUNING BERT-BASED MODELS FOR SENTIMENT ANALYSIS
KIBERNETYKA TA SYSTEMNYI ANALIZ · 2026 · 20-29
DOI: 10.34229/kca2522-9664.26.2.2 ↗Kurz gefasst
Fachartikel in der Zeitschrift KIBERNETYKA TA SYSTEMNYI ANALIZ, 2026. Verfasst von A.V. Anisimov und 3 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben.
Abstract (Originalsprache)
The paper explores the task of determining the emotional tone of Ukrainian texts using large language models. A comparative analysis of the performance of various BERT-based models is conducted. The impact of hyperparameter values on classification accuracy is examined. The paper proposes splitting texts into segments and compares different aggregation methods of representations to improve the accuracy of sentiment detection in long texts. Keywords: artificial intelligence, computational linguistics, neural network.
Zitieren
APA
Anisimov, A., Marchenko, O., Nasirov, E., & Taranukha, V. (2026). TUNING BERT-BASED MODELS FOR SENTIMENT ANALYSIS. KIBERNETYKA TA SYSTEMNYI ANALIZ, 20-29. https://doi.org/10.34229/kca2522-9664.26.2.2
Vancouver
Anisimov A, Marchenko O, Nasirov E, Taranukha V. TUNING BERT-BASED MODELS FOR SENTIMENT ANALYSIS. KIBERNETYKA TA SYSTEMNYI ANALIZ. 2026:20-29. doi:10.34229/kca2522-9664.26.2.2
BibTeX
@article{Anisimov2026,
author = {Anisimov, A.V. and Marchenko, O.O. and Nasirov, E.M. and Taranukha, V.Y.},
title = {TUNING BERT-BASED MODELS FOR SENTIMENT ANALYSIS},
journal = {KIBERNETYKA TA SYSTEMNYI ANALIZ},
year = {2026},
pages = {20--29},
doi = {10.34229/kca2522-9664.26.2.2}
}
EUVIMED