Similarity analysis of court judgments using clustering of case citation data: a study

Abstract

Information retrieval (IR) is an automatic mechanism to extract required information from a collection of unstructured or semi-structured data. IR systems minimize the effort of a user to locate the information based on the requirements. Clustering of documents is carried out as a preprocessing step for filtering irrelevant information in an IR system. Legal domain is a producer as well as consumer of huge in-formation which also contains invaluable legal knowledge and its interpretation. Knowledge based legal information retrieval systems is need of the day. Citation analysis is a technique to find the hidden relationships between the documents and is used for understanding knowledge transfer across various domains and hence becomes very important in legal domain. In this study, similarities among documents are analyzed using data clustering when applied on data of citations in court judgments.

Multilingual Analysis of Macrostructure in Online Lower Court Judgments of England and Wales, Germany, France and Spain: A Comparative Summary and Phraseology

“…They contribute towards automated identification of legal principles and facts within common law citations. This automated-based study is also observed in Kachappilly and Wagh (2018), who include a study of the IR (Information Retrieval), an automatic tool to extract and filter irrelevant information. Hunter (2015) has a different contribution to the study of court judgments.…”

PRILJ: an efficient two-step method based on embedding and clustering for the identification of regularities in legal case judgments

“…Clustering techniques have also been adopted in the legal field. Despite the fact that legal documents are highly abstract, researchers managed to group similar legal documents on the basis of their topics, or on the basis of case citations and legal citations (Conrad et al 2005;Lu et al 2011;Raghav et al 2015;Kachappilly and Wagh 2018). Conrad et al (2005) adopted a clustering tool (Zhao et al 2005) to apply both hard and soft clustering on three large heterogeneous datasets to effectively generate a taxonomy while supporting legal firms in their knowledge management processes.…”

“…A new clustering algorithm was also proposed, based on the Jaccard coefficient, and cluster prototypes were defined by selecting the legal case judgment exhibiting the highest similarity with the other legal case judgments within the cluster. Analogously, also Kachappilly and Wagh (2018) used case citations when clustering legal case judgments from the Indian Constitution. The proposed approach transforms the dataset into a binary matrix, indicating the presence or the absence of a citation of each case.…”

Assessment of text clustering approaches for legal documents

“…Em [Fan et al 2010], [Raghav et al 2015] e em [Kachappilly and Wagh 2018], o agrupamento é realizado levando em consideração a abordagem de que "dois objetos são similares se eles estão relacionados por objetos similares". Fan et al [Fan et al 2010] realiza o agrupamento de textos de leis levando em consideração as relações referenciais entre essas leis, enquanto que Raghav et al [Raghav et al 2015] e Kachappilly e Wagh [Kachappilly and Wagh 2018] realizam o agrupamento de julgamentos levando em consideração as citações desses documentos. Os três trabalhos utilizam técnicas de agrupamento com o objetivo de auxiliar os profissionais na tarefa de identificação de objetos similares.…”

“…Esses documentos são dados valiosos para todos os agentes envolvidos no meio jurídico, pois processos anteriores que são semelhantes a novos processos podem conter informações que oferecem suporte à tomada de decisão. No entanto, para ter acesso a essas informações, os profissionais precisam procurar os processos semelhantes em uma vasta coleção de documentos que estão em sua maioria no formato de linguagem natural (documentos textuais), o que dificulta a análise e interpretação desses resultados [Kachappilly and Wagh 2018].…”