EPSRC DTP PhD studentship: Detecting and preventing criminal network involvement from digital footprints

University of Exeter - College of Engineering, Mathematics and Physical Sciences

Main supervisor: Dr Miriam Koschate-Reis (University of Exeter)
Co-supervisor: Prof Mark Levine (University of Exeter)
Co-supervisor: Prof Richard Everson (University of Exeter)

Project Description:

This PhD project will develop and refine socio-technical approaches to detecting and understanding collective identities online. The focus of the work will be on promoting intervention to prevent illegal activities and involvement in criminal networks. The PhD will build on recent (EP/J005053/1) and ongoing research (EP/K033433/1) in this area.

The project will combine cutting edge social psychological theory on social identity and online behaviour, with developments in the analysis of social media data and with advances in machine learning. The research will combine online experiments of the expression of social identities in social media data (e.g. linguistic fingerprint of group norms, faking of identities), with micro analysis of a corpus of social media data (which has, in part, already been assembled as a research resource). The insights from theory and from empirical analysis will be worked up and fed into a toolkit for detecting various digital group identities. Technical challenges include the extraction of data from social media and the integration of social psychological knowledge with machine learning techniques. The project will use social media data in an iterative manner. By using emails from ENRON employees (a dataset that we already have available), predictions from social identity theory can be compared with predictions from alternative theories (e.g. social network analysis). Next, we will create a mathematical model for detecting criminal group identities online. This model will then be used to trace individuals’ commitment and involvement in criminal networks. The PhD project will bring an innovative interdisciplinary approach to the problem of detecting criminal networks online.

Importantly, the programme of research will also tackle the challenging question of the legal and ethical use of social media data to understand psychological aspects that an individual did not intend to reveal.

This project is designed to be undertaken by the student as the main researcher. Hence, the student will be expected to familiarise themselves with the relevant literature in social psychology, sociology and linguistics. They will then be supervised to undertake mathematical modelling of the existing dataset on ENRON email exchanges. We will then develop new hypotheses with them that might require experimental data collection and/or further social media data/data from the National Crime Agency. After an initial period of close supervision, we expect the student to become increasingly independent as a researcher and determine the direction the project will be taking. The student will also be the person to lead communication with colleagues from the National Crime Agency.

The student will gain insights into interdisciplinary research that brings together computer science, mathematics and social sciences. They will be learn about cutting edge mathematical models of machine learning and natural language processing and how these can be fruitfully applied to understanding social media data in novel ways. In addition, they will profit from a thorough theoretical grounding in psychological, sociological and sociolinguistic theories of identity. The collaboration with the National Crime Agency will allow them to gain insights into careers outside academia that require doctoral level skills and interdisciplinary working.

Share this PhD
     
  Share by Email   Print this job   More sharing options
We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

PhD

Location(s):

South West England