Machine Learning-Based Analysis of Public Sentiment on Cyber Security Issues via Social Media

DOI

10.2991/978-94-6463-764-9_3How to use a DOI?

Keywords

Sentiment Analysis; Cyber Security; VADER; Machine Learning; Public Opinion

Abstract

Cybersecurity has become a critical issue in today’s digital era. This study aims to analyze public sentiment toward cybersecurity issues on social media using a text mining approach. Data were collected through scraping from Twitter, resulting in 935 tweets containing relevant information about cyber-security. The data were preprocessed by removing punctuation, stopwords, and normalization, followed by sentiment labeling using the VADER method to classify sentiments as positive, neutral, or negative. The analysis was performed using machine learning algorithms, including Naive Bayes, Support Vector Machine (SVM), Random Forest, Logistic Regression, and K-Nearest Neighbors (KNN). Of the total data, 80% were used for training and 20% for testing. The sentiment distribution in the test data was 73 positive, 11 neutral, and 20 negative sentiments. Random Forest achieved the highest accuracy on the training data, while SVM demonstrated superior performance on the test data. Logistic Regression achieved a precision of 68.3%, recall of 76.9%, and F1 Score of 70.8%, with an overall accuracy of 76.9%. The accuracy for other models is as follows: Logistic Regression (77.9%), SVM (77.9%), Random Forest (78.8%), Naive Bayes (75.0%), and KNN (69.1%). The analysis highlights the effectiveness of these models in classifying public sentiments toward cybersecurity, despite challenges posed by imbalanced data distribution.

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  - Basirudin Ansor
AU  - Muhammad Zainudin Al Amin
AU  - Maulana Sihdi Habibie
AU  - Raina Artika Ramadlonia
AU  - Dhendra Marutho
AU  - Atika Mutiarachim
PY  - 2025
DA  - 2025/07/30
TI  - Machine Learning-Based Analysis of Public Sentiment on Cyber Security Issues via Social Media
BT  - Proceedings of the 3rd Lawang Sewu International Symposium on Engineering and Applied Sciences (LEWIS-EAS 2024)
PB  - Atlantis Press
SP  - 14
EP  - 27
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-764-9_3
DO  - 10.2991/978-94-6463-764-9_3
ID  - Ansor2025
ER  -