Administrative sources on crimes (statistics on felonies and crimes) have in many cases shown to be unsatisfactory for the purpose of a scientific description of the criminal phenomenon. Specifically in the context of organized crime in Italy (and Mafia in particular) these sources show significant limits in terms of reliability and quality of the information due to specific recipients of data and to the difficulty in collecting and comparing data, as consequence of the speed of legislative changes and changes in criteria used to classify the data. This paper reports a research project based on analyzing criminal sentences on organized crime activities in Sicily, pronounced from 2000 through 2006. For this case study we split the analysis of a 1147 document textual corpus into three main stages. First, we collected criminal sentences from the various courthouses. Since there is not yet a unified digital archive of criminal sentences in Sicily, we collected them in their paper format and stored into digital format, then into plaintext, by means of computer technology. In the second stage, the text was examined in order to extract the actors involved in the facts and the relationships between them. The actors have been labelled with the following roles: judge, members of the court, prosecutor, defendants, lawyers. Actors not labelled have been purged from the analysis. Relationships between actors were also extracted in terms of close co-occurance in the text, and the network was investigated using social network analysis, leading to a social network of typical properties. In this paper, we report and discuss the sociological and computational approaches to characterize the social structure of criminal phenomena, using large-scale and automated computer tools.

Information Extraction and Social Network Analysis of Criminal Sentences. A sociological and Computational Approach

DE FELICE, DEBORAH;GIUFFRIDA, GIOVANNI;Giura G;
2013-01-01

Abstract

Administrative sources on crimes (statistics on felonies and crimes) have in many cases shown to be unsatisfactory for the purpose of a scientific description of the criminal phenomenon. Specifically in the context of organized crime in Italy (and Mafia in particular) these sources show significant limits in terms of reliability and quality of the information due to specific recipients of data and to the difficulty in collecting and comparing data, as consequence of the speed of legislative changes and changes in criteria used to classify the data. This paper reports a research project based on analyzing criminal sentences on organized crime activities in Sicily, pronounced from 2000 through 2006. For this case study we split the analysis of a 1147 document textual corpus into three main stages. First, we collected criminal sentences from the various courthouses. Since there is not yet a unified digital archive of criminal sentences in Sicily, we collected them in their paper format and stored into digital format, then into plaintext, by means of computer technology. In the second stage, the text was examined in order to extract the actors involved in the facts and the relationships between them. The actors have been labelled with the following roles: judge, members of the court, prosecutor, defendants, lawyers. Actors not labelled have been purged from the analysis. Relationships between actors were also extracted in terms of close co-occurance in the text, and the network was investigated using social network analysis, leading to a social network of typical properties. In this paper, we report and discuss the sociological and computational approaches to characterize the social structure of criminal phenomena, using large-scale and automated computer tools.
2013
organized crime ; criminal sentences ; network analysis
File in questo prodotto:
File Dimensione Formato  
informatica e diritto.pdf

solo gestori archivio

Tipologia: Versione Editoriale (PDF)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.41 MB
Formato Adobe PDF
1.41 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/39594
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact