On the Use of Fuzzy Clustering in Name Disambiguation
Main Article Content
Abstract
Resolving name ambiguity has become one of the most demanding problems in this era of information overload. This also affects literature management services like digital libraries. It is important to discern ambiguous publications and authors because uncertainty about the real authors of a publication sometimes lead to wrong credits to authors or otherwise. Previous studies have tried to solve this problem by using traditional computational techniques. Soft computing techniques like rough sets, genetic algorithms, fuzzy clustering, etc. promises to be a good option one can look forward to deal with the problems of uncertainty. In this paper, we present the result of our ongoing work for resolving name ambiguity problem in digital citations. We propose a name disambiguation model that uses a mix of hard and fuzzy clustering in a two stage framework. The results of our name disambiguation approach which we obtained on DBLP data are very encouraging and we have been able to achieve very good disambiguation performance in comparison to other baseline methods. Though the results before fuzzy clustering were also very good but after fuzzy clustering the proposed method was able to improve the results. On an average the values of Precision, Recall and F1 were 96.35, 94.01 and 94.72 percent respectively.
Â
Keywords: name disambiguation; ambiguous authors; two stage clustering; digital libraries
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.