%0 Journal Article %1 borges2011classification %A Borges, Eduardo N. %A Becker, Karin %A Heuser, Carlos A. %A Galante, Renata %D 2011 %E White, Bebo %E Isaías, Pedro %E Santoro, Flávia Maria %J Proceedings of the IADIS International Conference WWW/Internet 2011 %K bibliographic classification detection duplicate metadata %P 221--228 %T A Classification-based Approach for Bibliographic Metadata Deduplication %U http://www.eduardo.c3.furg.br/arquivos/download/www-internet2011.pdf %X Digital libraries of scientific articles describe them using a set of metadata, including bibliographic references. These references can be represented by several formats and styles. Considerable content variations can occur in some metadata fields such as title, author names and publication venue. Besides, it is quite common to find references that omit same metadata fields such as page numbers. Duplicate entries influence the quality of digital library services once they need to be appropriately identified and treated. This paper presents a comparative analysis among different data classification algorithms used to identify duplicated bibliographic metadata records. We have investigated the discovered patterns by comparing the rules and the decision tree with the heuristics adopted in a previous work. Our experiments show that the combination of specific-purpose similarity functions previously proposed and classification algorithms represent an improvement up to 12% when compared to the experiments using our original approach.

@article{borges2011classification, abstract = {Digital libraries of scientific articles describe them using a set of metadata, including bibliographic references. These references can be represented by several formats and styles. Considerable content variations can occur in some metadata fields such as title, author names and publication venue. Besides, it is quite common to find references that omit same metadata fields such as page numbers. Duplicate entries influence the quality of digital library services once they need to be appropriately identified and treated. This paper presents a comparative analysis among different data classification algorithms used to identify duplicated bibliographic metadata records. We have investigated the discovered patterns by comparing the rules and the decision tree with the heuristics adopted in a previous work. Our experiments show that the combination of specific-purpose similarity functions previously proposed and classification algorithms represent an improvement up to 12% when compared to the experiments using our original approach. }, added-at = {2012-03-05T15:51:37.000+0100}, author = {Borges, Eduardo N. and Becker, Karin and Heuser, Carlos A. and Galante, Renata}, biburl = {https://www.bibsonomy.org/bibtex/28f87206e413c2c632b5c633f484fcbe2/jaeschke}, editor = {White, Bebo and Isaías, Pedro and Santoro, Flávia Maria}, interhash = {ca7720210214f632758211735154eea2}, intrahash = {8f87206e413c2c632b5c633f484fcbe2}, journal = {Proceedings of the IADIS International Conference WWW/Internet 2011 }, keywords = {bibliographic classification detection duplicate metadata}, pages = {221--228}, timestamp = {2014-07-28T15:57:31.000+0200}, title = {A Classification-based Approach for Bibliographic Metadata Deduplication}, url = {http://www.eduardo.c3.furg.br/arquivos/download/www-internet2011.pdf}, year = 2011 }