Web Crawler System for Distinct Author Identification in Bibliographic Databases.

A person's name is regularly used to uniquely identify himself/herself from others; unfortunately names are in no way unique and this leads to serious problems. For instance, when trying to retrieve papers from academic database repositories, it can be difficult to distinguish one author from another if the individuals in question have the exact same name. An author can also assume another name, for instance by using the full name. Thus, being able to differentiate which person a specific name is referring to can be tricky. In this paper, we propose a method to solve this ambiguity problem by gathering information from bibliographic databases and using this information to create a social network tree. Based on the relationships created among co-authors it is possible to disambiguate authors with a high-level of accuracy. [ABSTRACT FROM AUTHOR]