International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | EmoSense AI |
|---|---|
| ABSTRACT | The rapid growth of digital communication platforms such as social media, customer feedback systems, online reviews, and chat applications has resulted in massive volumes of text data, making accurate emotion and sentiment understanding essential for enhancing user experience, decision-making, and intelligent system responses. Traditional sentiment analysis methods mainly perform basic polarity classification and often fail to capture deeper emotional context, sarcasm, and subtle language nuances, reducing their effectiveness on informal, ambiguous, and context-dependent real-world text. To address this limitation, this paper proposes a context-aware emotion and sentiment analysis system using modern Natural Language Processing supported by transformer-based deep learning models, aiming to accurately identify both sentiment polarity and underlying human emotions. Unlike keyword-based or manually engineered approaches, the transformer architecture analyzes relationships between words, enabling better interpretation of complex sentence structures, informal expressions, and sarcastic language. The system features a web-based frontend and a high-performance backend for real-time analysis, supporting both single-sentence input and batch processing through structured data files, making it suitable for academic and practical applications. Experimental evaluations demonstrate that the proposed approach delivers more reliable and consistent results than traditional machine-learning methods, effectively detecting multiple emotions, sarcasm, and context-sensitive language, thereby confirming that transformer-based models significantly enhance emotional understanding in text and provide a scalable, reliable solution for applications such as customer feedback analysis, social media monitoring, and intelligent conversational systems. |
| AUTHOR | K. VISHNU, DR. B. NARASIMHAN Student, Department of Computer Applications, Sri Ramakrishna College of Arts and Science, Coimbatore, India Assistant Professor, Department of Computer Applications, Sri Ramakrishna College of Arts & Science, Coimbatore, India |
| VOLUME | 181 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1402042 |
| pdf/42_EmoSense AI.pdf | |
| KEYWORDS | |
| References | [1] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the NAACL-HLT Conference, pp. 4171–4186. https://doi.org/10.18653/v1/N19-1423 [2] Jurafsky, D., & Martin, J. H. (2024). Speech and Language Processing. Pearson Education, 3rd Edition. [3] Wolf, T., Debut, L., Sanh, V., et al. (2020). Transformers: State-of-the-Art Natural Language Processing. Proceedings of the EMNLP Conference, Volume 1, Issue 2, pp. 38–45. [4] Pang, B., & Lee, L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends® in Information Retrieval, Now Publishers, pp. 1–135. |
