Investigation of related research is a very important task for researchers. In recent years, databases of academic papers have been developed, and researchers can search for related research using keywords and so on. However, it is a very time-consuming task to discover appropriate papers exhaustively from a large number of academic papers, classify them, and understand their contents. We have been researching methods that can properly extract papers of related research from an academic paper database. After finding those papers, researchers need to understand the relationship between those papers. We believe that there are several types of relations between papers that appear in citation expressions of related papers. In this paper, automatic classification of citation expressions is performed as the first step in the analysis of citation expressions, and the analysis results of each cluster are reported.
