Identifying Corroborated and Contradicted Claims Among Witness Statements Using Post-Hoc Collective Intelligence
Dean J. Jones, Gunjan Mansingh · 2018 IEEE 5th International Congress on Information Science and Technology (CiSt) · 2018
Humans are unable to effectively process large volumes of data and tend to employ heuristics such as availability and anchoring in their judgement, introducing predictable cognitive biases. These biases are more pronounced when there are time constraints and lead to errors in judgement with life-changing consequences when they occur in the context of the justice system. We briefly describe a framework dubbed Post-Hoc Collective Intelligence (PHCI) and investigate how it can be applied to the analysis of witness statements. In the following case, multiple statements about an incident are submitted. Through experimentation, we show that PHCI can be successfully applied to the problems of identifying internal and external inconsistencies and predicting false witness statements.