Scholarlink

<p>The paper examines the problem of identifying the emotional tone of Ukrainian texts utilizing large language models. It presents a comparative analysis of the performance of various BERT-based models and investigates the impact of hyperparameter values on classification accuracy. This paper proposes splitting texts into segments and compares different methods for aggregating segment representations in order to improve the accuracy of sentiment detection in long texts.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Tuning Bert-based Models for Sentiment Analysis of Texts

  • 期刊论文

  • 发表日期：

    2026年3月1日

查看全文
  • A. V. Anisimov,
  • O. O. Marchenko,
  • E. M. Nasirov,
  • V. Y. Taranukha

摘要

The paper examines the problem of identifying the emotional tone of Ukrainian texts utilizing large language models. It presents a comparative analysis of the performance of various BERT-based models and investigates the impact of hyperparameter values on classification accuracy. This paper proposes splitting texts into segments and compares different methods for aggregating segment representations in order to improve the accuracy of sentiment detection in long texts.