An Efficient Technique for Author Name Disambiguation

Scholarly digital libraries have become an important source of bibliographic records for scientific communities. Author name search is one of the most common query exercised in digital libraries. The name ambiguity problem in the context of author search in digital libraries, arising from multiple authors sharing the same name, poses many challenges. A number of name disambiguation methods have been proposed in the literature so far. A variety of bibliographic attributes have been considered in these methods. However, hardly any effort has been made to assess the potential contribution of these attributes. We, for the first time, evaluate the potential strength and/or weaknesses of these attributes by a rigorous course of experiments on a large data set. We also explore the potential utility of some attributes from different perspective. A close look reveals that most of the earlier work require one or more attributes which are difficult to obtain in practical applications. Based on this empirical study, we identify three very common and easy to access attributes and propose a two-step hierarchical clustering technique to solve name ambiguity using these attributes only. Experimental results on data set extracted from a popular digital library show that the proposed method achieves significantly high level of accuracy (> 90%) for most of the instances.