A Hybrid Approach to Interpretable Analysis of Research Paper Collections

Abstract

We define and find a most specific generalization of a fuzzy set of topics assigned to leaves of the rooted tree of a taxonomy. This generalization lifts the set to a "head subject" in the higher ranks of the taxonomy, that is supposed to "tightly" cover the query set, possibly bringing in some errors, both "gaps" and "offshoots". Our method involves two more automated analysis techniques: a fuzzy clustering method, FADDIS, involving both additive and spectral properties, and a purely structural string-to-text relevance measure based on suffix trees annotated by frequencies. We apply this to extract research tendencies from two collections of research papers: (a) about 18000 research papers published in Springer journals on data science for 20 years, and (b) about 27000 research papers retrieved from Springer and Elsevier journals in response to data science related queries. We consider a taxonomy of Data Science based on the Association for Computing Machinery Classification of Computing System (ACM-CCS 2012). Our findings allow us to make some comments on the tendencies of research that cannot be derived by using more conventional techniques.