Application of Topic Models to Judgments from Public Procurement Domain

TL;DR

This paper demonstrates how combining LDA with keyword extraction enhances theme detection and trend analysis in legal judgments from public procurement, aiding legal research and information retrieval.

Contribution

It introduces a novel approach integrating LDA with keyword extraction to improve interpretability and performance in analyzing legal texts.

Findings

Enhanced interpretability of topics

Detection of recurring themes and trends

Potential for improved legal information retrieval

Abstract

In this work, automatic analysis of themes contained in a large corpora of judgments from public procurement domain is performed. The employed technique is unsupervised latent Dirichlet allocation (LDA). In addition, it is proposed, to use LDA in conjunction with recently developed method of unsupervised keyword extraction. Such an approach improves the interpretability of the automatically obtained topics and allows for better computational performance. The described analysis illustrates a potential of the method in detecting recurring themes and discovering temporal trends in lodged contract appeals. These results may be in future applied to improve information retrieval from repositories of legal texts or as auxiliary material for legal analyses carried out by human experts.