Text Mining for the Analysis of Legal Texts

Words are the main tool of a lawyer. The analysis of a large amount of textual information makes up the lion's share of legal practice, in particular, when creating an evidence base in criminal proceedings, analyzing pre-trial decisions, analyzing court decisions in similar cases, observing judicial precedent, etc. There are many answers to essential questions hidden in these documents. Every year, the number of legal and law-related electronic text documents that need to be quickly and efficiently analyzed is growing exponentially. Using powerful Text Mining tools will help you discover important legal information and make the right legal decisions.Automatic text classification is one of the most effective tools for finding and analyzing information in jurisprudence. This article presents a Decision tree model using the Chi-square Automatic Interaction Detector (CHAID) growing method for classifying legal texts. A model for automatic classification of text documents related to criminal proceedings has been developed for the dataset of 1,800 text documents used in court proceedings in Ukraine from 2000 to 2020.