Main Trends in the Development of Criminological Theory and Crime Prevention Practice in the Context of the Digitalization of Society

The digitalization of society, associated with a large-scale introduction of digital technologies in all socially relevant spheres, not only brough about positive changes, but also had a powerful effect on the transformation of crime and criminogenic factors. This has created an urgent need for understanding the prospects of criminological science in the new conditions, for strengthening its role in ensuring national security, for improving its methodology in new ways. The authors define key criminal threats to the security of the digital space: a rapid increase of its criminalization due to the features attractive for criminals (trans-national character of cyberspace, widespread anonymization and encryption, digital means of committing crimes and concealing their traces, etc.); the emergence and widening of criminogenic zones of cyberspace, with DarkNet holding a special place; the use of «digital» methods of resisting law enforcement, including cryptocurrencies and artificial intelligence. It is concluded that the abovementioned circumstances make it necessary to change the methodology of criminological research and the practice of law enforcement. The collection and generalization of information from publicly available digital sources, its analysis with the use of big data acquire a special research potential connected with the possibility of finding hidden regularities and obtaining criminological knowledge that cannot be found elsewhere. The digitalization of society creates conditions for the introduction of a preventive model of law enforcement based on predictive analysis methods. It becomes possible to quickly detect signs of criminal activity that require both a specific reaction of law enforcement and systemic managerial decisions. It also opens broad prospects for predicting individual criminal behavior by analyzing the Internet activity of specific individuals. The authors then highlight the most relevant directions for the development of criminological theory and the practice of crime prevention in the conditions of the digitalization of society.

Accuracy of Prediction by Machine Learning Algorithms

Over the past few decades, Machine Learning (ML) has evolved from the endeavor of few computer enthusiasts exploiting the possibility of computers learning to play games, and a part of Mathematics (Statistics) that seldom considered computational approaches, to an independent research discipline that has not only provided the necessary base for statistical-computational principles of learning procedures, but also has developed various algorithms that are regularly used for text interpretation, design recognition, and a many other commercial purposes and has led to a separate research interest in data mining to identify hidden regularities or irregularities in social data that growing by second. This paper efforts on explaining the concept and evolution of Machine Learning, some of the popular Machine Learning algorithms and try to compare three most popular algorithms based on some basic notions. Sentiment140 dataset was used and performance of each algorithm in terms of training time, prediction time and accuracy of prediction have been documented and compared.