Sentiment Analysis in Social Media Text Using NLP

DOI

10.2991/978-94-6239-654-8_41How to use a DOI?

Keywords

Sentiment analysis; Emotional detection; text classification; machine learning; classification algorithms; feature selection; NLP

Abstract

The rapid increasing social media has resulted in the creation of huge amounts of multilingual user-generated content, which complicates the task of sentiment analysis with the occurrence of such issues as language diversity, informal style of writing, use of slangs, transliteration, and often, code-mixing. Conventional machine learning and deep learning methods such as SVM, CNN, and LSTM usually lack the capability of contextual meaning across languages and this leads to a decline in the classification accuracy. This study seeks to overcome these shortcomings by proposing an NLP transformer-based model (with the BERT (Bidirectional Encoder Representations in Transformers model) to perform multilingual sentiment analysis of social media text. The bidirectional attention mechanism of BERT allows a deep contextual interpretation of words in sentences and is therefore very useful in semantically understanding relationships in mixed and low-resource language conditions. The suggested methodology implies the use of preprocessing (noise elimination, text normalization and tokenization) and then refining multilingual BERT (mBERT) with a multilingual sentiment set. Empirical analysis of BERT with metrics like accuracy, precision, recall, and F1-score proves that the method is far superior to the traditional methods since it is able to provide better sentiment classification performance on a variety of linguistic inputs.

Copyright

© 2026 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  - S. Shanmugavalli
AU  - V. Khanaa
PY  - 2026
DA  - 2026/04/24
TI  - Sentiment Analysis in Social Media Text Using NLP
BT  - Proceedings of the Global Conference on Sustainable Energy Systems, Smart Electronics and Intelligent Computing (GCSESEIC 2025)
PB  - Atlantis Press
SP  - 508
EP  - 519
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-654-8_41
DO  - 10.2991/978-94-6239-654-8_41
ID  - Shanmugavalli2026
ER  -