A DATA-DRIVEN APPROACH TO PUBLIC SAFETY EVENT DETECTION USING NLP TECHNIQUES

Authors

  • Veeragoni Ramya Sri Vaageswari College of Engineering(Autonomous) Author
  • Dr. P. Venkateshwarlu Vaageswari College of Engineering(Autonomous) Author

Keywords:

Public Safety , Event Detection, Natural Language Processing (NLP) , Social Media Analysis, Machine Learning , Deep Learning , Text Mining , Named Entity Recognition

Abstract

This paper uses cutting-edge Natural Language Processing (NLP) to analyze massive amounts of unstructured text data from social media, news stories, and emergency communication logs to identify public safety incidents. Machine learning models like deep learning architectures, feature extraction, and preprocessing are used to identify and categorise safety-related events like accidents, crimes, and natural disasters in real time. The system improves situational awareness and early warning for authorities and first responders using sentiment analysis, named entity recognition, and topic modeling. Experiments show that NLP-driven monitoring systems are more precise, accurate, and responsive than traditional systems. This shows how important they are to proactive public safety management.

Author Biographies

  • Veeragoni Ramya Sri, Vaageswari College of Engineering(Autonomous)

    Department of MCA,

    Vaageswari College of Engineering(Autonomous), Karimnagar, TG.

  • Dr. P. Venkateshwarlu, Vaageswari College of Engineering(Autonomous)

    Professor, Department of MCA,

    Vaageswari College of Engineering(Autonomous), Karimnagar, TG.

Downloads

Published

2026-06-13