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 | Twitter Sentiment Analysis |
|---|---|
| ABSTRACT | In the modern digital era, social media platforms have become one of the most powerful sources for understanding public opinion and emotional responses toward real-world events, products, and trending topics. Among various platforms, Twitter is widely used for sharing instant thoughts and reactions, generating a continuous stream of live textual data. Analyzing this data manually is difficult due to its volume and speed. To address this challenge, this project proposes a Live Twitter Sentiment Analysis System developed using the Python programming language that automatically analyzes real-time tweets and categorizes them into positive, negative, and neutral sentiments. The main objective of this system is to perform sentiment analysis using live data instead of stored datasets, enabling dynamic and up-to-date analysis. The system connects to Twitter through an API to fetch tweets based on user-given keywords, hashtags, or headlines. Once the tweets are collected, several preprocessing techniques are applied, including text cleaning, removal of special characters, stop-word filtering, tokenization, and normalization. These steps help improve the quality of the data and enhance the accuracy of the sentiment classification process. Natural Language Processing (NLP) techniques and sentiment analysis models are then used to evaluate the emotional tone of each tweet. After classification, the analyzed results are presented visually through bar charts and pie charts, allowing users to quickly understand the distribution of sentiments. The use of graphical visualization makes the system user-friendly and helps in identifying trends and patterns effectively. The live visualization feature ensures that the sentiment results are updated continuously as new tweets are received, making the system suitable for real-time monitoring. |
| AUTHOR | M ISWARYA, 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.2026.1402040 |
| pdf/40_Twitter Sentiment Analysis.pdf | |
| KEYWORDS | |
| References | [1] Bing Liu, Sentiment Analysis and Opinion Mining,Morgan & Claypool Publishers, 2012. [2] Steven Bird, Ewan Klein, and Edward Loper, Natural Language Processing with Python, O’Reilly Media, 2009. [3] A. Pak and P. Paroubek, “Twitter as a Corpus for Sentiment Analysis and Opinion Mining,” Proceedings of the International Conference on Language Resources and Evaluation, 2010. [4] Tweepy Documentation, “Twitter API for Python Developers.” Available: https://docs.tweepy.org [5] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. |
