Automated Discovery of Logical Fallacies in Legal Argumentation

Abstract

This paper presents a model of an algorithmic framework and a system for the discovery of non sequitur fallacies in legal argumentation. The model functions on formalised legal text implemented in Prolog. Different parts of the formalised legal text for legal decision-making processes such as, claim of a plaintiff, the piece of law applied to the case, and the decision of judge, will be assessed by the algorithm, for detecting fallacies in an argument. We provide a mechanism designed to assess the coherence of every premise of a claim, their logic structure and legal consistency, with their corresponding piece of law at each stage of the argumentation. The modelled system checks for validity and soundness of a claim, as well as sufficiency and necessity of the premise of arguments. We assert that, dealing with the challenges of validity, soundness, sufficiency and necessity resolves fallacies in argumentation.