Clustering analysis for determining the key interests in the financial literature using text mining

New economy in the era of globalization once more attracts novel investment strategies with modern analysis methods. Data mining in the last decade has been a major source of strategy implementation process in banking sectors. The volume of unstructured textual data which was generated and stored previously, has been increasing rapidly on the web. Thus, the need for processing this vast amount of text is increasing also. Text mining aims to extract novel and useful information from large amount of unstructured textual data in a semi-automatic way. In this study, we perform text-mining steps on the corpus containing the abstracts of scientific articles of five major journals publishing in the finance, economics and banking fields. For clustering of terms and detecting main topics of text on the term - document data created by text mining processes k-means clustering and singular value decomposition (SVD) methods are applied. In this study, findings demonstrate that text mining can be a very useful tool to investigate the change of trends and summarization of literature.