{"ID":2883077,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08651","arxiv_id":"2508.08651","title":"Prompt-Based Approach for Czech Sentiment Analysis","abstract":"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.","short_abstract":"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,...","url_abs":"https://arxiv.org/abs/2508.08651","url_pdf":"https://arxiv.org/pdf/2508.08651v1","authors":"[\"Jakub Šmíd\",\"Pavel Přibáň\"]","published":"2025-08-12T05:31:07Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}