Identification of dependency patterns in research collaboration environments through cluster analysis

In this paper, we present a new way of detecting dependency patterns in research collaboration environments. We use co-authorship data at the organization level to measure the degree of research collaboration. Thus we adopt a special clustering technique, called 'cross-associations clustering', to extract the dependency patterns among research groups. To assist in evaluating the dependency patterns, we suggest a collaboration dependency index to indicate whether a research group is dependent on other groups. In our work, as target research environments, we choose four significant areas: alternative energy, water shortage, food shortage and global warming. Through extensive cluster analysis, we have found that dependency patterns exist in the areas of alternative energy, water shortage and global warming, but not in the food shortage area.