Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186466,
        author = {Shaurya Vardhan},
        title = {Comparative Analysis of Traditional Large Models and Large Language Models (LLMs) for Sentiment Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {1696-1697},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186466},
        abstract = {This paper explores the comparative effectiveness of traditional large models, such as BERT, and contemporary Large Language Models (LLMs) like GPT -3.5 and Llama2 in performing sentiment analysis on a Google Reviews dataset. Our study finds that for sentences with up to 40 keywords, traditional models perform on par with LLMs. However, for sentences exceeding 40 keywords, LLMs are essential for maintaining accuracy and efficiency. This finding highlights the potential for optimizing sentiment analysis tasks by strategically selecting models based on sentence length, thereby achieving a balance between cost - effectiveness and processing speed.},
        keywords = {BERT, Large Language Models, Sentiment Analysis, Comparative Study},
        month = {November},
        }