Do We Still Need Fine Tuning? Turkish Sentiment Analysis in the Era of Large Language Model
For researchers and practitioners in Turkish NLP, this work demonstrates that prompted LLMs are not yet a replacement for supervised fine-tuning in realistic sentiment analysis, especially when a neutral class is present.
The study compares classical ML, fine-tuned PLMs, and prompted LLMs for Turkish sentiment analysis on a three-class (negative, neutral, positive) e-commerce dataset. Fine-tuned BERTurk outperforms all prompted LLMs in the three-class task, with LLMs collapsing neutral reviews into polarized categories, showing that supervised fine-tuning remains necessary.
This study examines whether supervised fine-tuning remains necessary for Turkish sentiment analysis in the era of large language models. We compare classical machine learning methods, fine-tuned pretrained language models, and prompted large language models on a Turkish e-commerce review dataset with negative, neutral, and positive labels. Fine-tuned BERTurk models perform best overall and outperform all prompted large language models in the full three-class task. The neutral class emerges as the main difficulty: while several large language models are much more competitive in binary positive--negative classification, they degrade substantially in the three-class setting by collapsing neutral reviews into polarized categories. The findings suggest that, in realistic Turkish sentiment classification, prompted large language models do not yet match supervised fine-tuning in the zero-shot setting, and that including the neutral class is crucial for robust evaluation.