Author Matching Using String Similarities and Deep Neural Networks

DOI

10.2991/aisr.k.200424.073How to use a DOI?

Keywords

Author Name Disambiguation (AND), author matching, Deep Neural Network

Abstract

Author Name Disambiguation (AND) is one of the problems in the process of classification of publication data, where the introduction of the characteristics of each author is difficult to recognize because of the frequent changes in patterns in writing author names. In the world of publications, author classification is needed to classify authors with types and fields of science based on published papers, therefore in this paper the author will classify with the aim of providing definite values whether the author is with the paper title a and author a with the paper title b is the same person or not. The method used by the author is one branch of Deep Learning, namely the Deep Neural Network DNN). DNN is used because it has high data processing acceleration capabilities with the use of GPU technology. With this method, AND data classified by the author produces a high level of accuracy with a value of 98%.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zaqqi YAMANI
AU  - Siti NURMAINI
AU  - FIRDAUS
AU  - M Naufal R
AU  - Winda Kurnia SARI
PY  - 2020
DA  - 2020/05/06
TI  - Author Matching Using String Similarities and Deep Neural Networks
BT  - Proceedings of the Sriwijaya International Conference on Information Technology and Its Applications (SICONIAN 2019)
PB  - Atlantis Press
SP  - 474
EP  - 479
SN  - 1951-6851
UR  - https://doi.org/10.2991/aisr.k.200424.073
DO  - 10.2991/aisr.k.200424.073
ID  - YAMANI2020
ER  -