Performance Analysis of Data Mining Algorithms

Abstract

The globalisation of Internet is creating enormous amount of data on servers. The data created during last two years is itself equivalent to the data created during all these years. This exponential creation of data is due to the easy access to devices based on Internet of things. This information has become a source of predictive analysis for future happenings. The versatile use of computing devices is creating data of diverse nature and the analysts are predicting the future trend using data of their respective domain. The technology used to analyse the data has become a bottleneck over the time. The main reason behind this is that the rate with which the data is getting created is much more than the technology used to access the same. There are various mining techniques used to explore the useful information. In this research there is detailed analysis of how data is used and perceived by various data mining algorithms. Mining algorithms like Naïve Bayes, Support Vector Machines, Linear Discriminant Analysis Algorithm, Artificial Neural Networks, C4.5, C5.0, K-Nearest Neighbour are analysed. The input data used in these algorithms is big data files. This research mainly focuses on how the existing data algorithms are interacting with big data files. The research has been done on twitter comments.