Detecting Criminal Organizations
What better way to identify criminal networks than to use their communications against them? This is what forensic detectives in law enforcement have used to trace who knows who in the network and potentially identify the crime lord. Since criminals use mobile phones in this day-in-age, it allows detectives to track their metadata and find out who they were in contact with. This presents the opportunity for SNA to shine in terms of using phone call record metadata to identify a potential structure of the criminal network itself.
Is there a way to detect a criminal organization network from phone call records?
By using LogAnalysis and communication data, criminal network structures can be unveiled to support law enforcement agencies with investigations.
The data in this case study were based off the results of a previous forensic investigation. The authors note for the sake of privacy protection, some information was obscured. In other words, potentially phone call metadata was used for the purpose of walking through this
Network metrics like degree centrality, betweenness, closeness, and eigenvector centrality were analyzed in this study and modeled in LogAnalysis. This software is what forensic detectives use in the analysis of phone log records by means of a network representation. Nodes signify each unique cell phone (belonging to the criminals) whereas the edges represent the phone calls between the phones. The researchers went into extensive depth into their methodology of algorithm selection, clustering, and cutoff in the dendogram below. In the interest of keeping this blog post condensed, I won’t dive further into the intricate details of what else the authors did. But the takeaway is that their methodology has the potential of identifying (sub)groups of a crime network by using LogAnalysis and phone call records.
Ferrara, E., De Meo, P., Catanese, S., & Fiumara, G. (2014). Detecting criminal organizations in mobile phone networks. Expert Systems with Applications, 41(13), 5733-5750. doi:10.1016/j.eswa.2014.03.024
Preventing Adolescent Problem Behavior
Deviancy training is the concept where the communication of antisocial topics among peers lead to the encouragement and instruction for how to engage in these antisocial behaviors. With middle school being a pivotal period where friendships are chosen that promote problematic behavior, DeLay et al. decided to test if an intervention could impact this cycle.
Can a school-based intervention affect middle school friendship choices and, in turn, have a lasting impact on deviant talk with friends?
Assignment to the intervention would affect friendship choices.
Students from three middle schools were randomly assigned to participate in the study, where approximately 500 of 998 were placed in the intervention group while the rest were in the control group. The intervention group was placed in the SHAPe, a 6-week curriculum designed to engage parents and students to promote school success, healthy adolescent choices, and other methods that diminish problem behaviors. The control group was not introduced to SHAPe. At least one cohort of students were put through this study. Students were to self-report or be observed on the following: affiliation with deviant peers, friendship nominations, friendship interaction, deviancy training, and socioeconomic status. The students were followed up five years after the initial time of study.
A longitudinal social network approach within RSiena (empirical network analysis package) was used to simultaneously account for and unravel selection from influence effects. The nodes were the students and the edges represent their friendships. Their findings suggest that public middle school intervention can change middle school, yet there is a bit of conflict in this finding. Only one of the three schools showed the intervention to influence friendship choices. There were also many limitations to this study, like how a great deal of turnover in friendships occurred over the five years… as we all have realistically gone through at this age.
DeLay, D., Ha, T., Van Ryzin, M., Winter, C., & Dishion, T. J. (2015). Changing Friend Selection in Middle School: A Social Network Analysis of a Randomized Intervention Study Designed to Prevent Adolescent Problem Behavior. Prevention Science, 17(3), 285-294. doi:10.1007/s11121-015-0605-4