Sentiment Analysis: a Comparative Study in Real-time Analysis

DOI

10.2991/978-94-6463-866-0_61How to use a DOI?

Keywords

Sentiment Analysis; Social Media; Twitter (X); VADER; RoBERTa; Natural Language Processing (NLP); Transformer Models; Lexicon-based Approach; Real-time Analysis

Abstract

In the era of rapid digital communication, social media platforms like Twitter (now X) serve as critical channels for public opinion and discourse. This project presents a comprehensive sentiment analysis pipeline that integrates both lexicon-based and transformer-based natural language processing (NLP) techniques to evaluate sentiments expressed in tweets and user comments. Utilizing the VADER (Valence Aware Dictionary for Sentiment Reasoning) sentiment analyzer alongside the pre-trained RoBERTa model, we perform dual-perspective sentiment classification to enhance reliability and contextual understanding. A dataset comprising tweet texts with associated sentiment labels was used for exploratory data analysis, followed by visualization of sentiment distributions, temporal trends, and model correlation. Additionally, real-time scraping and sentiment analysis of a live Twitter thread were conducted using Selenium to demonstrate the pipeline’s applicability in dynamic social media environments. Sentiments of both the original post and its replies were analyzed and compared. Word frequency distribution and word cloud visualizations further revealed the linguistic patterns associated with different sentiment classes. This hybrid approach not only improves sentiment classification performance but also provides a valuable framework for real-time social media monitoring, public opinion mining, and digital humanities research.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - K. Akila
AU  - Amanpreet Kaur
AU  - Shreyan Jana
AU  - Avinash Singh
PY  - 2025
DA  - 2025/10/31
TI  - Sentiment Analysis: a Comparative Study in Real-time Analysis
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 747
EP  - 759
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_61
DO  - 10.2991/978-94-6463-866-0_61
ID  - Akila2025
ER  -