A Text Mining Algorithm Optimising the Determination of Relevant Studies

In this paper, we develop a text mining algorithm that influences the identification of relevant literature studies. The algorithm consists of three processes, detection process; preparation process; and mining process. The detection process includes the determination of document language and abstract and keywords. The Preparation includes the processes, split content to paragraphs; paragraph length determination; converting text to lower case; text typography factor; content tokenization, removing stop words. Finally, the mining includes the processes, regular expression; normalization; grouping and computing frequency. The proposed algorithm would be useful in providing an alternative means of searching highly relevant content from large databases.