Exploring the potential of Natural Language Processing techniques in criminal justice agencies: An investigation of racial disparities in release decisions from the Parole Board

All Criminal Justice agencies generate voluminous records documenting the characteristics of cases processed and decisions adopted. There is a long tradition of manually processing such records using content analysis, coding relevant text information into statistical datasets. The key problem with these techniques lies in their scalability. The cost/time of processing records manually is directly proportional to the number of cases to be processed. Following advances in the field of Data Science and Artificial Intelligence, we propose the exploration of text-mining techniques to undertake coding processes automatically.

Building on previous work, and partnering with The Parole Board, this project will push the methodological frontier in this crucial research area. The Parole Board conducts risk assessments to decide whether prisoners can be safely released into the community. In their latest annual exercise The Parole Board processed 16,436 ‘paper-hearings’ for which short structured textual summaries were routinely recorded. These ‘hearing summaries’ capture the main characteristics of the case, together with demographic factors of the prisoner including ethnicity.

Analysing a significant sample of these ‘hearing summaries’, the project objectives are: i) develop text-mining algorithms capable of processing ‘hearing summaries’; ii) assess the reliability of the data these algorithms generate; and iii) analyse the data they produce to explore potential racial disparities in Parole Board decisions.

Project reference: LE43

Deadline 14th April