Clustering of Brazilian legal judgments about failures in air transport service: an evaluation of different approaches

• Published in: Artificial intelligence and law Vol. 30; no. 1; pp. 21 - 57
• Main Authors: Sabo, Isabela Cristina, Dal Pont, Thiago Raulino, Wilton, Pablo Ernesto Vigneaux, Rover, Aires José, Hübner, Jomi Fred
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.03.2022; Springer; Springer Nature B.V
• Subjects: Air transportation; Algorithms; Artificial Intelligence; Cluster analysis; Clustering; Complexity; Computer Science; Customer service; Entropy; Information Storage and Retrieval; Intellectual Property; IT Law; Judgments; Judicial statistics; Labels; Laws, regulations and rules; Legal Aspects of Computing; Machine learning; Media Law; Philosophy of Law; Purity; Remedies; Review Article; Santa Catarina Brazil; Brazil; K-means; Air transport service; Lingo; Affinity Propagation; Hierarchical Clustering; Consumer law; Unsupervised learning
• ISSN: 0924-8463; 1572-8382
• DOI: 10.1007/s10506-021-09287-3

The paper presents different clustering approaches in legal judgments from the Special Civil Court located at the Federal University of Santa Catarina (JEC/UFSC). The subject is Consumer Law, specifically cases in which consumers claim moral and material compensation from airlines for service failures. To identify patterns from the dataset, we apply four types of clustering algorithms: Hierarchical and Lingo (soft clustering), K-means and Affinity Propagation (hard clustering). We evaluate the results based on the following criteria: (1) entropy and purity; (2) algorithm's ability in providing labels; (3) legal expert’s evaluation; and (4) experimental complexity. The results demonstrate that the most advantageous approach is Hierarchical Clustering, since it has the best entropy and purity numbers, as well as the least difficulty for the expert to analyze the clusters, and the least experimental complexity. The main contribution of the paper is to show the advantages and disadvantages of each approach, especially to identify labels in unstructured and non-indexed legal texts.