Performance of Multiple String Matching Algorithms in Text Mining

摘要

Ever since the evolution of Internet Information retrieval is being made by surfers in large amount. The data gets increased everyday as the thirst of acquiring knowledge by the users gets increased day-by-day. The data which is raw needs to be processed for usage which increases the potential value in all major areas like Education, Business etc. Therefore Text Mining is an emerging area where unstructured information were made as relevant information. Text mining process can be divided into Information Extraction, Topic Tracking, Summarization, Categorization, Clustering, concept Linkage and Information visualization. Even though all other things can be applied to text only properly it is extracted from the web. Using Pattern matching or String matching algorithms to retrieve proper results from the Sea of information. In this paper we discuss the three types of algorithms Aho Corasick, Wu Manber and Commentz Walter. The performance of the algorithms are identified by implementing it in Python language. Finally the suitable algorithm for extracting information is found.