A Multimodal and Multilingual NLP Framework for Real-Time Sentiment Analysis and Dynamic Public Opinion Modeling across Social Media Platforms

S. Kannadhasan, Guruprasad Konnurmath, A. Mohana Selvan, Sriram M., Allam Balaram

2025

Abstract

With the emergence of social media in the past few years, the generation and propagation of public opinion takes a format that begs for efficient tools to measure and understand these types of ‘sentiment trends’ as these take place. This article presents a new NLP framework with multilingual, multimodal, and real-time capabilities for analyzing sentiment across diverse social media networks. Unlike previous methods, this enables models to incorporate both textual information and emojis, hashtags and/or images in their predictions to better understand the context of the sentiment, especially in informal or sarcastic texts. By utilising transformer-based architectures and explainability methodologies, the proposed approach not only provides accurate prediction but also explains to some extent. Furthermore, it characterizes the dynamic of public opinion, and recognises the key opinion changes occurring during events like election, social movement and crisis. The model is trained and validated with cross-talk, diversity large-scale indicating multi-language/cross-culture across platforms, which is robust and general. This all-in-one solution solves existing problems and establishes the new state-of-the-art for live sentiment analytics and public trend predictions with NLP.

Paper Citation

in Harvard Style

Kannadhasan S., Konnurmath G., Selvan A., M. S. and Balaram A. (2025). A Multimodal and Multilingual NLP Framework for Real-Time Sentiment Analysis and Dynamic Public Opinion Modeling across Social Media Platforms. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 264-271. DOI: 10.5220/0013862400004919

in Bibtex Style

@conference{icrdicct`2525,
author={S. Kannadhasan and Guruprasad Konnurmath and A. Selvan and Sriram M. and Allam Balaram},
title={A Multimodal and Multilingual NLP Framework for Real-Time Sentiment Analysis and Dynamic Public Opinion Modeling across Social Media Platforms},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={264-271},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013862400004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25
TI - A Multimodal and Multilingual NLP Framework for Real-Time Sentiment Analysis and Dynamic Public Opinion Modeling across Social Media Platforms
SN - 978-989-758-777-1
AU - Kannadhasan S.
AU - Konnurmath G.
AU - Selvan A.
AU - M. S.
AU - Balaram A.
PY - 2025
SP - 264
EP - 271
DO - 10.5220/0013862400004919
PB - SciTePress