An Information Extraction Model Using a Graph Database to Recommend the Most Applied Case

Legal researchers spend too much time on locating the most applied case. The purpose of this paper is to present a comprehensive model to assist legal researchers in accessing legal data, specifically the most applied case for a field of law. An extensive critical review of the literature was conducted to identify the status of research in this field. The findings revealed that existing studies did not present models to specifically recommend the most applied case, nor did they indicate database methods to store and query legal documents. The model was derived based on the findings from the literature review and extended to include the adoption of a graph database for information storage. A case study approach was used to empirically test the concepts. Testing was limited to a small number of documents as proof of concept and future research will test for scalability. The model can contribute to the research community in the fields of information retrieval, information extraction, database retrieval methods, as well as the legal domain. For legal researchers, the findings can be used to assist them with the process of accessing the most applied case quickly and reducing time spent searching.