DataSpeak: Data Extraction, Aggregation, and Classification Using Big Data Novel Algorithm

Abstract

A huge amount of data is coming due to large set of computing devices. As a birth of the variety of data, data processing and analysis is a big issue in big data analytics. On other hand, data consistency and scalability is also a major problem in the large set of data. Our research and proposed algorithm aims to data extraction, aggregation, and classification based on novel approach as “DataSpeak”. We have used k-Nearest Neighbors with Spark as reference and produced a novel approach with modified algorithm. We have analyzed our approach on the large dataset from travel and tourism, placement papers, movies and historical, smartphone, etc., domains. As for ability and accuracy of our algorithm, we have used cross validation, precision, recall, and comparative statistical analysis with the existing algorithm. Our approach returns with the fast accessing of data with efficient data extraction in a minimal time when compared to the existing algorithm in same domain. As concerned with the data aggregation and classification, our approach returns 98% of data aggregation and classification based on the data structure.