Home // DATA ANALYTICS 2019, The Eighth International Conference on Data Analytics // View article

Automated Extraction of Domain-Specific Information from Scientific Publications

Authors:
Philipp Kief
Clarissa Marguardt
Katja Nau
Steffen Scholz
Andreas Schmidt

Keywords: Named entities; Domain specific entities; Entity cooccurrence; Visualization

Abstract:
As the number of scientific publications in many subject areas continues to increase, it is becoming more and more important to support researchers in filtering out relevant information from papers and to identify relevant papers as well. In the present work, the field of nanotoxicology is used to investigate how dictionary-based disambiguation and extraction of entities of the domain can be implemented and how information on entire scientific papers can be extracted. By developing an analysis tool, it can be shown that the automated analysis of scientific publications in the field of nanotoxicology can be realized in basic terms. The analysis tool is based on the General Architecture for Text Engineering (GATE), D3.js and additional Node.js services, as well as Angular.js and represents an application that can be controlled intuitively by thescientists and provides a suitable user interface to visualize the extracted information in an aggregated way.

Pages: 43 to 48

Copyright: Copyright (c) IARIA, 2019

Publication date: September 22, 2019

Published in: conference

ISSN: 2308-4464

ISBN: 978-1-61208-741-2

Location: Porto, Portugal

Dates: from September 22, 2019 to September 26, 2019