VALA2022 Onsite Session 18 Chadwick

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

VALA2022 Onsite Session 2 Chadwick

Koha for a cataloguing agency: considerations and challenges for a system implementation during COVID lockdown

This session is sponsored by IEEE Xplore

VALA2022 CONCURRENT 2
Tuesday 14 June 2022, 14:10 – 14:40

Ben Chadwick

  • Director, Research and Information Services
  • Education Services Australia
Chris Cormack
  • Technical Lead – Koha Team
  • Catalyst IT
Aleisha Amohia
  • Koha Development Lead
  • Catalyst IT

Please tag your comments, tweets, and blog posts about this session: #vala2022 #s2

Read the paper and view the presentation recording and slides here:

Abstract

In 2020, the Schools Catalogue Information Service (SCIS) commenced a project to replace its existing cataloguing system with Koha, an open-source library management system. Catalyst was appointed to undertake the installation, data migration and integration with SCIS’s existing systems, as well as providing training and ongoing support. This paper describes the project-management process and how it was adapted to accommodate COVID-19 lockdowns. It outlines customisations and additional developments undertaken to support SCIS’s specific needs and workflows, and further work and on-going support arrangements in the post-launch phase.

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.

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.

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).

 

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License

VALA2020 Session 4 Chadwick

New values: supporting value-added data through the SCIS APIs

VALA2020 CONCURRENT SESSION 4
Tuesday 11 February 2020, 11:25 – 11:55

Ben Chadwick
  • Manager, Research and Information Services
  • Education Services Australia

Please tag your comments, tweets, and blog posts about this session: #vala2020 #s7

Read the paper, view the video of the presentation on the VALAView channel and view the presentation slides here:

Abstract

Until 2017 the Schools Catalogue Information Service (SCIS) used the library industry standards MARC-21 and z39.50 to transmit data to subscribers’ local school library systems. SCIS launched a new platform in July 2017 and a set of APIs in March 2018, for the first time offering alternative transmission options compliant with ubiquitous web standards. These developments enabled SCIS to add value to its data, remove impediments to access, support on-the-fly provision of metadata for online resources, and pave the way for further innovations around RDA. This paper describes the new SCIS online services and the factors driving them.

 

This work is licensed under a Creative Commons Attribution-NonCommercial License.

VALA2018 Session 11 Chadwick

vala conf home button
vala peer reviewed
Ben Chadwick 120
Ben Chadwick

SCIS Resource Type Thesaurus: a linked data vocabulary for inferring Resource Type from MARC records

VALA2018 CONCURRENT SESSION 11
Wednesday 14 February 2018, 14:45 – 15:15

Ben Chadwick

Education Services Australia

Please tag your comments, tweets, and blog posts about this session: #vala2018 #s27

Abstract

Resource Type (RT) is a multifaceted concept that is encoded in a range of elements in Machine-Readable Cataloging (MARC) records. However, expressions of RT are often unhelpful to users, and many records are inconsistent in how they represent it. The Schools Catalogue Information Service (SCIS) Resource Type thesaurus (SRT) is a linked data thesaurus defining RT categories, enabling searching, limiting, sorting and faceting by RT in the SCIS online catalogue. Semantic relations within SRT enable mappings to and from the thesaurus in spite of variations across legacy and current MARC records. The purpose, design, and possible applications of SRT are discussed.

 

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial License.