Beyond administrative reports: a deep learning framework for classifying and monitoring crime and accidents leveraging large-scale online news
Issued Date
2025-01-01
Resource Type
ISSN
09410643
eISSN
14333058
Scopus ID
2-s2.0-85217855208
Journal Title
Neural Computing and Applications
Rights Holder(s)
SCOPUS
Bibliographic Citation
Neural Computing and Applications (2025)
Suggested Citation
Tuarob S., Tatiyamaneekul P., Pongpaichet S., Tawichsri T., Noraset T. Beyond administrative reports: a deep learning framework for classifying and monitoring crime and accidents leveraging large-scale online news. Neural Computing and Applications (2025). doi:10.1007/s00521-024-10833-8 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/105390
Title
Beyond administrative reports: a deep learning framework for classifying and monitoring crime and accidents leveraging large-scale online news
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
The escalating prevalence of violent crimes and accidents underscores the urgent need for efficient and timely monitoring systems. Traditional methods reliant on administrative reports often suffer from significant delays. This paper proposes CRIMSON, a novel framework that leverages large-scale online news to provide real-time insights into crime and accident trends. CRIMSON utilizes a multi-label classification technique that leverages a fine-tuned, pre-trained, cross-lingual language model to accurately categorize news articles. Our experimental results, conducted on a substantial dataset of Thai news articles, demonstrate superior performance, achieving an average F1 score of 86%. Beyond classification, CRIMSON aggregates categorized news into real-time statistics, revealing strong correlations between news-reported incidents and official crime data. This study pioneers online news as a reliable and timely crime and accident monitoring source, offering valuable insights for law enforcement, policymakers, and researchers.