Volltext-Downloads (blau) und Frontdoor-Views (grau)

Zoonosis Text Mining: Scraping infection data of rabies from scientific articles and integrating them into the Open Research Knowledge Graph

  • With the growing scientific output that is produced, its getting more important to automate the extraction of knowledge from articles. This bachelor thesis will describe an approach doing exactly this. Scientific articles will be obtained from a database. These articles will be preprocessed to gain a set of training data, to update a language model that already exists for Python library spaCy. The model will be trained to recognize different sorts of entities regarding to the virus rabies. After this process the model will be used for ten articles and the extracted knowledge will be used to extend the Open Research Knowledge Graph.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Joshua Thos
Document Type:Bachelor Thesis
Year of first Publication:2022
Date of final exam:2022/04/12
First Referee:Konrad FörstnerGND
Advisor:Eva Seidlmayer
Degree Program:Data and Information Science
Language:English
Page Number:30
Tag:Natural Language Processing; Open Research Knowledge Graph; spaCy
GND Keyword:Text Mining; Tollwut
Institutes:Institut für Informationswissenschaft der TH Köln
URN:urn:nbn:de:hbz:79pbc-opus-19014
Licence (German):License LogoCreative Commons - Namensnennung-Weitergabe unter gleichen Bedingungen