Machine learning for classifying bibliographic resources: using topical headings to infer alignments to Australian Curriculum learning areas
VALA2022 CONCURRENT 18
Wednesday 15 June 2022, 15:50 – 16:20
Ben Chadwick
- Director, Research and Information Services
- Education Services Australia
Please tag your comments, tweets, and blog posts about this session: #vala2022 #s18
Read the paper and view the presentation recording and slides here:
Abstract
Since 2017 the Schools Catalogue Information Service (SCIS) has enabled users to search the SCIS catalogue by curriculum learning area. A rules-based algorithm is used to infer the learning area to which records are aligned. This paper explores the possibility of using machine learning to supplement or replace the current approach. Multi-label supervised classifiers were trained on topical headings from a large dataset of digital learning resources from the Scootle repository. They were then tested on a smaller set of SCIS records and demonstrated adequate results for a subset of learning areas, with better precision than recall. Methods for improving classification are discussed.
Biography
Dr Ben Chadwick is Director, Research and Information Services at Education Services Australia where he oversees the Schools Catalogue Information Service (SCIS) and the Australian Education Vocabularies (IEV), including the linked data Schools Online Thesaurus (ScOT). Ben grew up on Turrbal/Jagera country but now lives on Wurundjeri land, in Brunswick East, with his partner, two daughters and a greyhound.
Aleisha Amohia (Te Ātihaunui-a-Papārangi) (she/her) is a Koha Developer at Catalyst IT in Wellington, New Zealand. She has been working on Koha since 2014. Aleisha recently graduated from Victoria University of Wellington with a Bachelor of Science (Computer Science and Artificial Intelligence) and a Bachelor of Commerce (Management and Information Systems).
Chris Cormack is of Kāi Tahu, Kāti Māmoe and Waitaha descent. He has 24 years experience working in the ICT sector, with 21 of those being in the Library ICT sector. He was one of the original developers of the Koha library management system, started in Horowhenua and now used by over 15,000 libraries worldwide. Chris started his professional career working for Te Pūtahi a Toi at Massey University after completing his studies for a Bachelor of Science in Computer Science and a Bachelor of Arts in Māori Studies and Mathematics. He programmed the backend of the Toi te Kupu system (a catalogue of resources in te reo Māori and for the teaching of te reo Māori) Chris is now Kaihuawaere Matihiko at Catalyst IT.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License