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{187781,
        author = {AMAN KUMAR and Arihant Jain and Animesh Singh Gosain},
        title = {Sentiment Analysis Of Healthcare Tweets Using Transformer-Based and Domain-Adapted IndicBERT},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {6},
        pages = {6388-6394},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187781},
        abstract = {Healthcare-related conversations on social media provide important insight into public opinion, patient experience, and emerging health issues. However, sentiment classification of healthcare tweets is challenging due to noise, code-mixing, informal expressions, and domain-specific vocabulary. This paper presents a transformer-based sentiment analysis system that compares classical machine-learning models with modern transformer architectures, with special focus on a domain-adapted IndicBERT model optimized for Indian healthcare discourse. A curated dataset of healthcare tweets was preprocessed and annotated for three sentiment classes. Models including Logistic Regression, SVM, mBERT, DistilBERT, and IndicBERT were evaluated through accuracy, F1-score, and error analysis. Results show that IndicBERT, when adapted with healthcare-specific vocabulary and fine-tuning, outperforms both classical approaches and general-purpose transformers. The study demonstrates the value of domain adaptation for transformer models in specialized sectors such as healthcare and highlights the suitability of IndicBERT for analyzing multilingual, code-mixed Indian tweets. The findings support applications in public-health monitoring, sentiment tracking, and automated decision-support systems},
        keywords = {Healthcare sentiment analysis, transformer models, IndicBERT, multilingual NLP, code-mixed text, contextual embeddings, sentiment classification.},
        month = {January},
        }