An efficient approach for storage of court judgements using graph database Online publication date: Mon, 23-May-2022
by Varsha Mittal; Durgaprasad Gangodkar; Bhaskar Pant
International Journal of Advanced Intelligence Paradigms (IJAIP), Vol. 22, No. 1/2, 2022
Abstract: Extracting relevant information from a large dataset has always been challenging and predicting is even more. One such issue comes with arranging large volume of court cases into meaningful data. Text mining approach has its own limitations when it comes to large volume of data having similar type of information. This paper aims at developing an e-dictionary for the courts using a simplified and case wise keyword dictionary creation that could be used to understand the judgements pronounced in earlier similar cases. To overcome the challenge of breaking the text into tokens and get the word count without compromising the speed, a single cluster on Hadoop is considered and finally graph database to store the data. The model is guided by various graph and set theories and is an effort to answer the queries of judges and lawyers in an effective manner by reducing the effort of reading the whole cases and referring only to the final judgement. Use of graph theory provides the logical view of the stored data. To check the robustness of the proposed model precision, recall, and accuracy were calculated and they were found to be 1.0, 0.92 and 92.66%, respectively.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Advanced Intelligence Paradigms (IJAIP):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com