Search results

The purpose of this paper is to develop a methodology for knowledge discovery in emergency response service databases based on police occurrence reports, generating information to help law enforcement agencies plan actions to investigate and combat criminal activities.

The developed model employs a methodology for knowledge discovery involving text mining techniques and uses latent Dirichlet allocation (LDA) with collapsed Gibbs sampling to obtain topics related to crime.

The method used in this study enabled identification of the most common crimes that occurred in the period from 1 January to 31 December of 2016. An analysis of the identified topics reaffirmed that crimes do not occur in a linear manner in a given locality. In this study, 40 per cent of the crimes identified in integrated public safety area 5, or AISP 5 (the historic centre of the city of RJ), had no correlation with AISP 19 (Copacabana – RJ), and 33 per cent of the crimes in AISP 19 were not identified in AISP 5.

The collected data represent the social dynamics of neighbourhoods in the central and southern zones of the city of Rio de Janeiro during the specific period from January 2013 to December 2016. This limitation implies that the results cannot be generalised to areas with different characteristics.

The developed methodology contributes in a complementary manner to the identification of criminal practices and their characteristics based on police occurrence reports stored in emergency response databases. The generated knowledge enables law enforcement experts to assess, reformulate and construct differentiated strategies for combating crimes in a given locality.

The production of knowledge from the emergency service database contributes to the government integrating information with other databases, thus enabling the improvement of strategies to combat local crime. The proposed model contributes to research on big data, on the innovation aspect and on decision support, for it breaks with a paradigm of analysis of criminal information.

The originality of the study lies in the integration of text mining techniques and LDA to detect crimes in a given locality on the basis of the criminal occurrence reports stored in emergency response service databases.

The purpose of this paper is to develop a method for the discovery of knowledge in emergency response databases based on police incident reports, generating information that identifies local criminal demands that allow the selection of the appropriate policing strategies portfolio to solve the problem.

The developed model uses a methodology for the discovery of knowledge involving text mining techniques using Latent Dirichlet Allocation (LDA) integrated with the ELECTRE I multicriteria method.

The developed method allowed the identification of the most common criminal demands that occurred from January 1 to December 31, 2016, in the policing areas studied. One of the crimes does not occur homogeneously in a particular locality. In this study, it was initially observed that 40 per cent of the crimes identified in the Integrated Public Safety Area 5, or AISP-5, (historical city center of RJ) had no correlation with AISP-19 (Copacabana - RJ), and 33 per cent of crimes crimes in AISP-19 were not identified in AISP-5. This finding guided the second part of the method that sought to identify which portfolio of policing strategies would be most appropriate for the identified demands. In this sense, using the ELECTRE I method, eight different scenarios were constructed where it can be identified that for each specific criminal demand set there is a set of policing strategies to be applied.

The collected data represent the social dynamics of neighbourhoods in the central and southern zones of the city of Rio de Janeiro during the specific period from January 2013 to December 2016. This limitation implies that the results cannot be generalised to areas with different characteristics.

The developed methodology contributes in a complementary way to the identification of criminal practices and their characteristics based on reports of police occurrences stored in emergency response databases. The knowledge generated through the identification of criminal demands allows law enforcement decision makers to evaluate and choose among the available policing strategies, which best suit the reality they study, and produce the reduction of criminal indices.

It is possible to infer that by choosing appropriate strategies to combat local crime, the proposed model will increase the population’s sense of safety through an effective reduction in crime.

The originality of the study lies in the integration of text mining techniques, LDA and the ELECTRE I method for detecting crime in a given location based on crime reports stored in emergency response databases, enabling identification and choice, from customized policing strategies to particular criminal demands.