Evaluating PEVNET: A framework for visualization of criminal networks

Abstract

Information visualization has been a burning topic among the researchers in the recent decade. Getting targeted information, which is everyone’s desire, is becoming difficult with the abundance of data. In this research, we have made an evaluation of our proposed framework PEVNET by conducting an experiment. Thirty two participants evaluated the system. The experiment was performed in two phases. In the first phase, a usability evaluation and qualitative feedback was carried out to check whether the PEVNET framework provided adequate results to the users. The qualitative feedback was performed by considering two aspects: the ease of use and the functionality. In the second phase, the comparison of the PEVNET had been performed against another state-of-the-art tool. Locating the central person, detecting the hidden interaction patterns between the sub-clusters, and detecting temporal activity were among the main tasks that were to be achieved by the participants. These tasks were to be performed in the groups of participants. The case study of Chicago Narcotics datasets was used. We found that the participants, of the PEVNET group, performed the tasks faster as compared to the other techniques used in the experiment. Among the participants, there were a few domain experts who appreciated our novel visualization features. Anecdotally, we believe that by evaluating the PEVNET in this research paper, we will be able to get the confidence of the crime analysts. We have found that the network visualization of the PEVNET framework, based on the experimental results, has gotten satisfactory feedback from the majority of the participants.