Natural Language Processing and Psychology in e-Government Services: Evaluation of a Crime Reporting and Interviewing System

Crime statistics from the US Bureau of Justice and the FBI Uniform Crime Report show a gap between reported and unreported crime. For police to effectively prevent and solve crime, they require accurate and complete information about incidents. This article describes the evaluation of a crime reporting and interviewing system that witnesses can use to report crime incidents or suspicious activities anonymously while ensuring the information received is of such quality that police can use it to begin an investigation process. The system emulates the tasks that a police investigator would perform by leveraging natural language processing technology and the interviewing techniques used in the Cognitive Interview. The system incorporates open-source code from the General Architecture for Text Engineering GATE program developed by researchers at the University of Sheffield, Web and database technology, and Java-based proprietary code developed by the author. Findings of this evaluation show that the system is capable of producing accurate and complete reports by enhancing witnesses' memory recall and that its efficacy approximates the efficacy of a human conducting a cognitive interview closer than existing alternatives. The system is introduced as the first computer application of the cognitive interview and proposed as a viable alternative to face-to-face investigative interviews.