Modeling Verdict Outcomes Using Social Network Measures: The Watergate and Caviar Network Cases

Abstract

Modelling criminal trial verdict outcomes using social network measures is an emerging research area in quantitative criminology. Few studies have yet analyzed which of these measures are the most important for verdict modelling or which data classification techniques perform best for this application. To compare the performance of different techniques in classifying members of a criminal network, this article applies three different machine learning classifiers–Logistic Regression, Naïve Bayes and Random Forest–with a range of social network measures and the necessary databases to model the verdicts in two real–world cases: the U.S. Watergate Conspiracy of the 1970’s and the now–defunct Canada–based international drug trafficking ring known as the Caviar Network. In both cases it was found that the Random Forest classifier did better than either Logistic Regression or Naïve Bayes, and its superior performance was statistically significant. This being so, Random Forest was used not only for classification but also to assess the importance of the measures. For the Watergate case, the most important one proved to be betweenness centrality while for the Caviar Network, it was the effective size of the network. These results are significant because they show that an approach combining machine learning with social network analysis not only can generate accurate classification models but also helps quantify the importance social network variables in modelling verdict outcomes. We conclude our analysis with a discussion and some suggestions for future work in verdict modelling using social network measures.

Sociometric network analysis in illicit drugs research: A scoping review

“…Looking at Colombia and Mexico, Garay-Salamanca and Salcedo-Albarán [ 68 ] used traditional SNA methods coupled with an innovative method called SNAID (Social Network Analysis for Institutional Diagnosis) to explain how criminal networks can affect democratic formal institutions. Furthermore, two studies looked specifically at court processes related to illicit drugs [ 52 , 77 ]. Looking at both individuals and organizations, Shomade [ 52 ] used quantitative analysis along with qualitative data description of one criminal and one drug court in the U.S. to shed light on the court structure and processes, as well as identify central members.…”

“…Looking at both individuals and organizations, Shomade [ 52 ] used quantitative analysis along with qualitative data description of one criminal and one drug court in the U.S. to shed light on the court structure and processes, as well as identify central members. Masias et al [ 77 ] used machine learning techniques and SNA to predict the verdict in the trial of a drug trafficking organization based in Canada.…”

A new technique for influence maximization on social networks using a moth-flame optimization algorithm

“…Hao et al introduced three measures of accuracy, sensitivity, and F1 value to quantitatively evaluate the results in finding influence. These criteria are defined as Table 1 [ 60 , 61 ]:…”

Modelling the Unit Property Prices in Türkiye Employing Deep Learning Methods

“…The housing prices in the UK is investigated in another study where the Gaussian process regression, regressionkriging, random forests and an M5P decision tree algorithms are compared and it is shown that the Gaussian process regression has the best accuracy [6]. In another work, the property prices in Santiago, Chile are modelled using neural networks, random forest search and SVM approaches considering over 16000 houses and it is concluded that the random forest method has the best performance [7]. The housing prices in Poland considering 12438 properties are modelled in another work using linear regression, decision trees and neural network methods where it is shown that the decision tree approach provides the best accuracy [8].…”