Data mining and visualization on legal documents

LIRFSS (Legal Information Retrieval and Focused Semantic Search) is a system that performs IR(Information Retrieval) and IE(Information Extraction) on Indian Supreme Court decisions, specifically on criminal cases related to murder and provide focused semantic search results, offering a high potential of assistance for judges, lawyers and citizens in getting access to law. In this paper, development process of LIRFSS is discussed. Appropriate information to be extracted for criminal cases such as date, location of occurrence and IPC (Indian Penal code)[1] sections were determined from a sample set of documents. Better instruments than manual browsing and other search methods are required to make the most out of freely available law on internet, therefore a semantic search is carried out using extracted information and most pertinent cases were returned as a result. As analyzing the vast volumes of data becomes increasingly difficult, so information visualization is also carried out in this paper and a new hypotheses is proposed and verified. From 20 training documents, a satisfactory amount of precision was obtained.

I. Introduction

Information Retrieval (IR) is the process of narrowing down vast unstructured documents into sets of documents relevant to a particular problem. With vast repositories of online legal information, IR speeds up the analysis considerably by reducing the number of documents for analysis.