This paper introduces the first prompt-based methods for aspect-based sentiment analysis and sentiment classification in Czech. We employ the sequence-to-sequence models to solve the aspect-based tasks simultaneously and demonstrate the superiority of our prompt-based approach over traditional fine-tuning. In addition, we conduct zero-shot and few-shot learning experiments for sentiment classification and show that prompting yields significantly better results with limited training examples compared to traditional fine-tuning. We also demonstrate that pre-training on data from the target domain can lead to significant improvements in a zero-shot scenario.
@article{arxiv.2508.08651,
title = {Prompt-Based Approach for Czech Sentiment Analysis},
author = {Jakub Šmíd and Pavel Přibáň},
journal= {arXiv preprint arXiv:2508.08651},
year = {2025}
}
Comments
Published in Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing (RANLP 2023). Official version: https://aclanthology.org/2023.ranlp-1.118/