• P. TAMILSELVAN
• DR.S.M. JAGATHEESAN

Huge data are been acquired by social medias regularly, analyzing the enormous data is a complex task, many data mining techniques are existing to overcome and analyze complex Task.Spark is one of the most prominent platforms for big data analysis framework which offers a bunch of magnificent functionalities for various machine learning errands going from regression, classification, and dimension reduction to clustering and rule extraction. In this contribution, explore from the computational perspective, the expanding body of the Apache Spark MLlib 2.0 as an open source, appropriated, scalable, and platform independent machine learning library. These studies explain the feature of latest things in big data machine learning research and give insights to future work. This study propose a novel framework that combines the distributive computational abilities of Apache Spark and the advanced machine learning architecture of a deep multilayer perception (MLP), utilizing the popular concept of Cascade Learning. The research work direct empirical analysis of framework on two genuine world datasets. The outcomes are encouraging and certify proposed framework, thus demonstrating that it is an improvement over traditional big data analysis methods that utilization either Spark frame work.

Apache Spark Frame Work, Multi Layer Perception, Cascade Learning.

"SOCIAL MEDIA BIG DATA ANALYSIS USING SPARK FRAMEWORK AND COMPLEX DATA MINING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 3, page no.657-669, March-2021, Available :http://www.jetir.org/papers/JETIR2103090.pdf

"SOCIAL MEDIA BIG DATA ANALYSIS USING SPARK FRAMEWORK AND COMPLEX DATA MINING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 3, page no. pp657-669, March-2021, Available at : http://www.jetir.org/papers/JETIR2103090.pdf