Abstract
Organizations have been challenged by the need to process an increasing amount of data, both structured and unstructured, retrieved from heterogeneous sources. Criminal investigation police are among these organizations, as they have to manually process a vast number of criminal reports, news articles related to crimes, occurrence and evidence reports, and other unstructured documents. Automatic extraction and representation of data and knowledge in such documents is an essential task to reduce the manual analysis burden and to automate the discovering of names and entities relationships that may exist in a case. This paper presents SEMCrime, a framework used to extract and classify named-entities and relations in Portuguese criminal reports and documents, and represent the data retrieved into a graph database. A 5WH1 (Who, What, Why, Where, When, and How) information extraction method was applied, and a graph database representation was used to store and visualize the relations extracted from the documents. Promising results were obtained with a prototype developed to evaluate the framework, namely a name-entity recognition with an F-Measure of 0.73, and a 5W1H information extraction performance with an F-Measure of 0.65.
Highlights
Input: a set of documents that are retrieved from police departments and open sources, in Portable Document Format (.pdf), Microsoft Word (.doc) and HTML format; Document preprocessing: enables a set of tasks for document processing and Natural Language Processing; Graph database representation: enables the semantic understanding of data retrieved using Named Entity Recognition (NER), Criminal-Term Extraction, Semantic Role Labelling (SRL), and 5W1H information extraction methods
For NER evaluation, manual annotation was performed against a set of criminalrelated documents after annotating the documents by identifying and classifying each sentence named-entity and entity types
The focus is on the Portuguese language, without discarding what has been done in other languages; The approaches applied to the criminal domain and related works were studied and analyzed; A survey of existing ETL, NLP, Graph Database approaches was made and, for each one, a list was presented, with the features that can be proposed, used or adapted; The SEMCrime framework solves an emerging and ambitious challenge regarding the processing of Portuguese unstructured criminal reports files, mainly because it is applied to a domain without a solid background and relevant work-related to the Portuguese language, despite the works already published and applied to other cases such as the English language
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. A systematic approach that ties together the criminal investigation and the computer science domains, focused on the analysis of criminal-related documents in the Portuguese language; An end-to-end framework to deal with several phases ranging from data extraction to knowledge representation into a graph database These phases can be summarized as follows: Informatics 2021, 8, 37. Input: a set of documents that are retrieved from police departments and open sources (online news about crimes), in Portable Document Format (.pdf), Microsoft Word (.doc) and HTML format; Document preprocessing: enables a set of tasks for document processing and Natural Language Processing; Graph database representation: enables the semantic understanding of data retrieved using Named Entity Recognition (NER), Criminal-Term Extraction, Semantic Role Labelling (SRL), and 5W1H information extraction methods. A dataset built by a set of documents, such as police reports, criminal and PGdLisboa (Procuradoria-Geral Distrital de Lisboa, in English: District Attorney of Lisbon) news
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
