This is a decommissioned version of ERA which is running to enable completion of migration processes. All new collections and items and all edits to existing items should go to our new ERA instance at https://ualberta.scholaris.ca - Please contact us at erahelp@ualberta.ca for assistance!
- 249 views
- 194 downloads
Using Artificial Neural Networks to Create and Assign Subject Headings to New Publications: A Review of the Literature
-
- Author(s) / Creator(s)
-
Artificial neural networks (ANNs) are complex systems of hardware and software that mimic intuitive learning and decision-making based on pattern recognition. Mathematical formulae are used to assign weights to each factor being evaluated for a decision. This review examines existing literature for trends in automating subject heading creation to determine if ANNs are a viable option for completing this task. By conducting a literature review to examine the current capabilities of ANNs, the syntax requirements of Library of Congress subject headings, and previously developed automation solutions for metadata, this paper assesses how well ANNs meet the criteria necessary for creating subject headings with greater efficiency than the current methods in place that involve human labour and judgement. The goal of this paper is to inspire further research into ANN architecture and construction for testing the viability of using ANNs in this manner.
-
- Date created
- 2019-02-08
-
- Subjects / Keywords
-
- Type of Item
- Conference/Workshop Poster