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{204500,
        author = {Nandini J and Dr Sukesha H A and Dr.krishna Kumar P R},
        title = {TRANSFORMER BASED SENTIMENT ANALYSIS SYSTEM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2422-2431},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204500},
        abstract = {Sentiment Analysis, also known as opinion mining, is a key application of Natural Language Processing (NLP) that focuses on identifying and classifying emotions expressed in textual data. With the rapid growth of digital platforms such as social media, e-commerce websites, and online forums, a large volume of user-generated content is produced every day. Analyzing this data manually is inefficient, which makes automated sentiment analysis systems essential. Traditional methods such as Naive Bayes and Logistic Regression often fail to capture contextual meaning, leading to limited accuracy.
This project proposes a sentiment analysis system using a pre-trained transformer-based model (RoBERTa), which effectively understands contextual relationships in text. The system performs preprocessing of input text, tokenization using the model tokenizer, and directly utilizes the pre-trained model for sentiment prediction without additional training. The model classifies text into positive, negative, or neutral categories based on contextual understanding.
The proposed approach improves accuracy and performance by leveraging large-scale pre-training, making it suitable for applications such as customer feedback analysis, product reviews, and social media monitoring.},
        keywords = {},
        month = {June},
        }