A Semantic Clustering Framework for Discovering Latent Offense Patterns: A Case Study of Thai Police Records
Digital · 18.08.2026 · 6 (3) · 69
DOI: 10.3390/digital6030069 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital, online erschienen am 18.08.2026. Verfasst von Krittakom Srijiranon und 4 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Thammasat University Research Fund.
Abstract (Originalsprache)
Crime offense descriptions are often recorded as unstructured text, making large-scale analysis and categorization difficult. This study proposes a semantic clustering framework for Thai crime offense descriptions using sentence embeddings, dimensionality reduction, and unsupervised clustering. Two datasets were obtained from Thonglor Metropolitan Police Station and Mueang Nonthaburi Police Station, Thailand. After preprocessing, the datasets contained 962 and 902 unique offense descriptions, respectively. Each description was transformed into a 768-dimensional embedding using SimCSE-PhayaThaiBERT. The embeddings were represented in Principal Component Analysis (PCA) Space and Uniform Manifold Approximation and Projection (UMAP) Space and clustered using K-Means, DBSCAN, HDBSCAN, and OPTICS. The results showed that UMAP Space generally provided more useful clustering results than PCA Space. Although DBSCAN achieved the highest internal clustering scores, it classified most records as noise. In contrast, HDBSCAN provided a more balanced result by maintaining strong clustering quality while retaining more records for interpretation. Qualitative analysis showed that the discovered clusters corresponded to meaningful offense categories. The proposed framework can support exploratory analysis of Thai crime records without requiring manually labeled data.
Förderung
- Thammasat University Research Fund
Zitieren
APA
Srijiranon, K., Tanantong, T., Keeratiwattapong, N., Chalarak, N., & Sangtongdee, U. (2026). A Semantic Clustering Framework for Discovering Latent Offense Patterns: A Case Study of Thai Police Records. Digital, 6(3), 69. https://doi.org/10.3390/digital6030069
Vancouver
Srijiranon K, Tanantong T, Keeratiwattapong N, Chalarak N, Sangtongdee U. A Semantic Clustering Framework for Discovering Latent Offense Patterns: A Case Study of Thai Police Records. Digital. 2026;6(3):69. doi:10.3390/digital6030069
BibTeX
@article{Srijiranon2026,
author = {Srijiranon, Krittakom and Tanantong, Tanatorn and Keeratiwattapong, Nattanon and Chalarak, Nawarerk and Sangtongdee, Usanut},
title = {A Semantic Clustering Framework for Discovering Latent Offense Patterns: A Case Study of Thai Police Records},
journal = {Digital},
year = {2026},
volume = {6},
number = {3},
pages = {69},
doi = {10.3390/digital6030069}
}
EUVIMED