This paper is providing an introduction to the text mining methodology. There are many different researches which applying machine learning to improve its management application efficiency in various domains. This research is utilizing text mining technology, including "two step auto-clustering", "glossaries aggregation", "TF-IDF" and so on, which collecting the homogeneous glossaries from articles, guiding to the literature cluster analysis based on the Social Science Citation Index (SSCI) database. The result discovered that the research domains of artificial intelligence, document pattern and financial related are the most prosperous fields on machine learning application, It is leading by information technology development progressing, web 2.0 is also a boost to research morale. All of these will become a power for important developing direction on machine learning in near future.