Applying automatic text-based detection of deceptive language to police reports: Extracting behavioral patterns from a multi-step classification model to understand how we lie to the police

Filing a false police report is a crime that has dire consequences on both the individual and the system. In fact, it may be charged as a misdemeanor or a felony. For the society, a false report results in the loss of police resources and contamination of police databases used to carry out investigations and assessing the risk of crime in a territory. In this research, we present VeriPol, a model for the detection of false robbery reports based solely on their text. This tool, developed in collaboration with the Spanish National Police, combines Natural Language Processing and Machine Learning methods in a decision support system that provides police officers the probability that a given report is false. VeriPol has been tested on more than 1000 reports from 2015 provided by the Spanish National Police. Empirical results show that it is extremely effective in discriminating between false and true reports with a success rate of more than 91%, improving by more than 15% the accuracy of expert police officers on the same dataset. The underlying classification model can be analysed to extract patterns and insights showing how people lie to the police (as well as how to get away with false reporting). In general, the more details provided in the report, the more likely it is to be honest. Finally, a pilot study carried out in June 2017 has demonstrated the usefulness of VeriPol on the field.