Comparisons of clustering SSCI journals by emerging hierarchical clustering, hierarchical clustering and minimum spanning tree

By reducing the processing data to be checked for clustering from O(N²) to O(N), emerging hierarchical clustering is a fast algorithm with explicit clustering results. During the processes of emerging clustering, characteristic numbers of clusters are obtained, which correspond to various resolution scales for viewing the system. And the emerging of clusters does not need pre-given clustering level or boundary condition assumptions as input. To demonstrate this method, Emerging clustering is used to classify SSCI journal system in terms of the aggregated ISI journal citation reports. By comparing the clustered intra-cluster similarity and time complexity of different methods, we show that emerging clustering gives a better classification of SSCI journal system than hierarchical clustering and minimum spanning tree clustering.