Analysis of Impact of stop words on domain specific document set

Data mining is a technique of data evaluation for discovering hidden patterns over the raw data. The data is found in unstructured manner in the real world, therefore for extracting the meaningful data contents form this raw data, the data mining methods and techniques are helpful.In this presented study the, the data mining techniques are utilized for finding the valuable contents from the text document. In order to find more informative contents from text directories, various text mining techniques are recently developed. These text mining techniques are efficient and providing efficient results. But in order to find the user query relevance data from huge amount of data contents is a complex issue in this domain. In this proposed work a new technique for text mining is introduced which is provide more relevant text documents according to the user query. The proposed text document retrieval methodology is developed in visual studio environment and performance of the proposed system is evaluated in terms of accuracy, error and the precision value of the text search. According to the obtained results the performance of the proposed system is adoptable for large text directories. We are using static approach so that we can check efficiency of search for the documents. We are searching the database with and without the stop words and compairing their results, by taking difference of overall time taken by search. The process will results in time graph and the most relevant result of search.