Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Natural Language Processing-Enabled Framework for Regional Crime Analysis Using Unstructured Text: A Case of Abuja, Nigeria

Domaine:

peace and securitynatural language processing

Type de record:

paper
Créateur:
JalDr.
Éditeur:
Sre
Hôte:
Background:Globally, criminal activities have significantly increased over the years, which makes the need for a reliable and insightful analytical approach increasingly vital to take proactive measures. Specifically, Abuja is one of the fastest-growing cities in sub-Saharan Africa. The city is however constrained by the current approaches in crime analysis toward proactive decision-making. Thus, presenting an ardent need for this research to provide safety and security to the civilian population, especially those within the crime-prone area(s). Objective:Objective of this research is to develop a framework for crime analysis by identifying the regional frequency of the crimes committed in some selected parts of Abuja, FCT. Method:This research with the aid of the Natural Language Processing approach, crime reports from 2015 to 2021 of Wuse, Garki, Gwagwalada, Nyanya, Maitama and Utako comprising murder, kidnapping, theft, juvenile delinquency and homicidal acts established by the Nigerian Police Command was used toextract textual data therefrom. Using Orange data mining, which is a python-based environment; the reports were transformed to and pre-processed. Thereafter, crimes were mapped regionally using a visually appealing visualization technique known as Word cloud. Results:This essentially, clustered crimes based on their frequencies and regionally. This approach revealed critical details required proffering insights towards decision-making required for crime mitigation. In addition, to ascertain the relationship between crime hotspots the police divisional stations and slum settlement in the study area. Conclusion:The higher education attainment will be the cure for criminal activities in Nigeria. Government should also create more jobs because high unemployment rates will compel people to commit crimes and this will increase crime rate in Nigeria. Lastly, there should be high budgetary provision towards poverty alleviation programme because higher poverty may lead to higher crimes rate due to depression or mental illness associated with being poor and this will decrease the rate of return of legal activities and more likely to increase return of illegal activities.

Visit

doi.org

Similaires

Natural Language Processing (NLP) Techniques for Afan Oromo Text AnalysisText Summarization in the Shona Language using Natural Language ProcessingEnhancing Natural Language Processing in Somali Text Classification: A Comprehensive Framework for Stop Word RemovalUsable Amharic text corpus for natural language processing applicationsA Smart Translation System between Hausa and English Language Text Using Natural Language Processing TechniquesGKokonya/Natural-Language-Processing-Multiclass-Text-Classifiation

Natural Language Processing (NLP) Techniques for Afan Oromo Text Analysis

Natural Language Processing (NLP) has emerged as a transformative tool for analyzing and understandi

Text Summarization in the Shona Language using Natural Language Processing

The rise of digital information in many languages, including Shona, highlights the significance of d

Enhancing Natural Language Processing in Somali Text Classification: A Comprehensive Framework for Stop Word Removal

Usable Amharic text corpus for natural language processing applications

A Smart Translation System between Hausa and English Language Text Using Natural Language Processing Techniques

This paper developed a smart system for translating Hausa and English language texts using Natural

GKokonya/Natural-Language-Processing-Multiclass-Text-Classifiation

Around 1 in 4 people will experience a mental health problem this year. Low-income countries have an