Analysis of Sentimental of Comments on Social Media using Machine Learning Techniques

DOI

10.2991/978-94-6463-738-0_6How to use a DOI?

Keywords

Deep Learning (DL); Machine Learning (ML); Logistic Regression (LR); K-nearest Neighbor Algorithm (KNN); Long Short-Term Memory (LSTM); Natural Language Processing (NLP)

Abstract

Sentiment analysis has become a very useful tool for understanding user feedback and sentiment expressed on social media platforms. This study focuses on analysing comments to classify sentiment using various ML and DL models, including RF, K-Nearest Neighbours (KNN), LR, Decision Trees, NB, and Long Short-Term Memory (LSTM). In order to compare these models, criteria like accuracy, precision, recall, and F1 score were used. The results demonstrate that Random Forest as best among all other models, achieving an accuracy of 89.22% and an F1 score of 89.20%, indicating its robustness in handling complex and high-dimensional data. KNN closely followed with an F1 score of 89.13%, showcasing its effectiveness in identifying patterns within the dataset. LSTM achieved a respectable performance with an F1 score of 77.09%, highlighting the potential of deep learning models for sequential data. Meanwhile, simpler models such as Logistic Regression (F1 score: 68.77%) and Naïve Bayes (F1 score: 62.34%) underperformed, likely due to their linear decision boundaries and independence assumptions, respectively. Decision Trees provided moderate results, with an F1 score of 74.49%. The results shows that number of methods, especially Random Forest, work best for classifying sentiment in social media comments. This study highlights the importance of using advanced algorithms and improving features to make sentiment analysis more accurate. These improvements can help provide better insights for tasks like analysing opinions, understanding customer feedback, and monitoring social media.

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  - Astitva Pathak
AU  - Yogesh Kumar Rathore
AU  - Ojas Tulswani
AU  - Munagala Suryanarayana Murthy
PY  - 2025
DA  - 2025/06/22
TI  - Analysis of Sentimental of Comments on Social Media using Machine Learning Techniques
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 58
EP  - 71
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_6
DO  - 10.2991/978-94-6463-738-0_6
ID  - Pathak2025
ER  -