Big Data Analysis for Unstructured Data in Nigeria Court System

Abstract: Big Data Analysis for unstructured data involves analyzing and processing large amounts of unstructured data, such as text, images, and audio, to extract meaningful insights and knowledge. Techniques used in big data analysis for unstructured data include Natural Language Processing (NLP), Computer Vision, and Speech Recognition. Big data analysis can be useful in the Nigerian court system for analyzing unstructured data, such as legal documents, witness statements, and court transcripts. The goal would be to identify patterns and relationships within the data that can help make more informed decisions, improve processes, and increase the efficiency of the court system. This paper presents an improved Hybrid model for legal case document classification. The system starts by collecting legal case documents from an online domain. The collected documents are in pdf format. The collected pdf files were converted to texts using a pdf miner library in python. The converted texts were used in creating tables using the pandas library. After the creation of the dataset table, the dataset was pre-processed by removing Nan values, and non-alphanumeric values, and also performing tokenization. The tokenized data was then passed into principal component analysis for the selection of important features. The selected features were then used in training an LSTM model for the classification of the legal case documents. The result of the LSTM is outstanding, having an accuracy of 98% for training. The model was deployed to the web, for easy execution, testing, and assessment. Keywords: Big Data, Legal Case, Principal Component Analysis, Long Short-Term Memory, Python flask. Title: Big Data Analysis for Unstructured Data in Nigeria Court System Author: C. Aloy-Okwelle, J. Palimote, O.P Nweke International Journal of Novel Research in Computer Science and Software Engineering ISSN 2394-7314 Vol. 10, Issue 3, September 2023 - December 2023 Page No: 44-50 Novelty Journals Website: www.noveltyjournals.com Published Date: 08-November-2023 DOI: doi.org Paper Download Link (Source) noveltyjournals.com