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{182991,
        author = {THADALA VEERA VENKATA RAMANA and DR.K.SWAPNA},
        title = {Sentiment Analysis of Customer Reviews Using Classical ML and Deep Learning (BERT)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {4331-4335},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182991},
        abstract = {In the age of online shopping and social media, customers frequently express their opinions through reviews, which are valuable for businesses to understand satisfaction and improve services. This project uses automated sentiment analysis to classify these reviews as Happy, Unhappy, or Neutral. Two approaches are explored: classical machine learning using TF-IDF with models like LinearSVC and SGDClassifier, and a deep learning method using BERT, a powerful language model from Hugging Face's Transformers library.The classical models offer speed and simplicity, especially for smaller datasets, while BERT provides greater accuracy by better understanding language context. To enhance usability, a Gradio-based web interface was developed for real-time sentiment prediction. Overall, the study finds that while classical models are efficient, BERT delivers superior performance, making it suitable when accuracy is a top priority.},
        keywords = {Sentiment Analysis, TF-IDF, LinearSVC, SGDClassifier, BERT, Transformers, Gradio.},
        month = {July},
        }