Data mining and text mining — A survey

In this paper we mainly focus on the techniques of data mining such as clustering, classification etc. In today's strategy it becomes a hectic task to gather, analyze and extract huge amount of datasets. So we use many efficient methods for the practical integration of the data. Some of the main techniques are fuzzy set theory, approximate reasoning, genetic algorithms etc. It is also useful for transformation to many fields and also decision making. It also enhances Knowledge discovery database(KDD) for retrieving the information from any kind of formats like graph, flow chart, video etc. This mainly focuses on the data mining methodologies to handle the huge amounts of data in logical and systematic manner.

I. Introduction

The main reason for using data mining is to collect the needed and useful information from vast and enormous amount of data. The sub domain used in extracting the unique text is called as text mining. This is used to retrieve the main texts from unstructured and semi-structured textual formats. Generally all data in the web and social media are available in the form of fuzzy and random manner. So the main aim is to establish a bridge and relationship among the texts, so that it becomes easier for human to understand and process it in a effective manner. This process is known as Knowledge discovery from texts(KDT).