A real-time heuristic-based unsupervised method for name disambiguation in digital libraries

Abstract

This paper addresses the problem of name disambiguation in the context of digital libraries that administer bibliographic citations. The problem occurs when multiple authors share a common name or when multiple name variations for an author appear in citation records. Name disambiguation is not a trivial task, and most digital libraries do not provide an efficient way to accurately identify the citation records for an author. Furthermore, lack of complete meta-data information in digital libraries hinders the development of a generic algorithm that can be applicable to any dataset. We propose a heuristic-based, unsupervised and adaptive method that also examines users’ interactions in order to include users’ feedback in the disambiguation process. Moreover, the method exploits important features associated with author and citation records, such as co-authors, affiliation, publication title, venue, etc., creating a multilayered hierarchical clustering algorithm which transforms itself according to the available information, and forms clusters of unambiguous records. Our experiments on a set of researchers’ names considered to be highly ambiguous produced high precision and recall results, and decisively affirmed the viability of our algorithm. Keywords: Digital libraries, Name disambiguation, Bibliographic data