A Combined Lexicon-Based and Machine-Learning Approach For Forecasting Political Security Risks

DOI

10.2991/978-94-6463-858-5_50How to use a DOI?

Keywords

Public Safety; Sentiment Analysis; National Security; Machine Learning (ML); Threat Prediction

Abstract

The internet plays a crucial role in ensuring public safety today. The U.S. Knowledge People group ranks digital threats alongside terrorism and other significant challenges. Securing a nation has become increasingly difficult, given the vast amount of information online, including misinformation, which can potentially fuel hatred and undermine public safety. This project aims to link emotions and opinions to national security threats, focusing on the impact of negative sentiments in online data, which can jeopardize public safety. It’s essential for experts to quickly identify and address these sentiments. While there is some correlation between emotions and public safety concerns, limited research has been conducted on the significance of these emotionswith security risks or how to predict their escalation. This idea proposes to use online news sentiment analysis to predict political security threats. The study highlights political security as a crucial public safety concern and uses real-world web news data to illustrate the efficacy of word analysis and machine learning (ML) in filling in data gaps. The study makes use of Random Forest-Decision Tree models, a standalone Random Forest model, and ensemble learning with a stacking classifier. The predictive capacity of the system is further increased by adding AdaBoost to this ensemble technique, providing more reliable threat estimates. The solution uses an easy-to-use Flask interface for user testing and an SQLite database for straightforward sign-ins and data interchange. This ensures a thorough assessment of the system’s usability and efficacy while improving model performance and offering a useful platform for actual user interactions.

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  - D. Bujji Babu
AU  - A. Suneetha
AU  - D. M. Senthil
AU  - Akula Thulasi
AU  - K. Kishore Babu
PY  - 2025
DA  - 2025/11/04
TI  - A Combined Lexicon-Based and Machine-Learning Approach For Forecasting Political Security Risks
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 576
EP  - 590
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_50
DO  - 10.2991/978-94-6463-858-5_50
ID  - Babu2025
ER  -