TEXT SUMMARIZATION AS AN EMPIRICAL LEGAL RESEARCH TOOL BASED ON MACHINE LEARNING ALGORITHMS

ABSTRACT

This paper aims to explore text summarization techniques as a tool for empirical legal research, creating a summary of the decisions given the phrases predictive power with regard to the decision outcome. A dataset of habeas corpus decisions prompted by innumerable courts in Brazil is used that explicitly cite the COVID pandemic as a reason for requesting the release of the patients. A predictive model is created and through this analysis we propose to find the arguments most correlated with the outcome. © 2022 Universidad Diego Portales. All rights reserved.