Introducing an automated subject classifier
VALA2016 CONCURRENT SESSION 11: Describing IT
Wednesday 10 February 2016, 13:45 - 14:15
Persistent URL: http://www.vala.org.au/vala2016-proceedings/vala2016-session-11-mitchell
Pru Mitchell, Tine Grimston and Robert Parkes
Australian Council for Educational Research, Vic
Please tag your comments, tweets, and blog posts about this session: #vala16 #s27
Read the paper, view the video of the presentation on the VALA2016 GigTV channel and view the presentation slides here:
- pdf VALA2016-Session-11-Mitchell-Paper (139 KB)
- video VALA2016-Session-11-Mitchell-Video
- VALA2016-Session-11-Mitchell-Slides (465 KB)
The library community understands the value of controlled vocabularies in enhancing resource discovery. There is, however, ongoing tension between that value and the cost of maintaining and applying specialist vocabularies. This paper presents the outcomes of a 2014-15 trial of automated subject indexing at the Australian Council for Educational Research. The integration of a machine learning classification tool has resulted in streamlined workflows and increased use of machine-readable data. Insights were gained into the decisions human indexers make in using a controlled vocabulary, and into the importance of quality abstracts and metadata.
This work is licensed under a Creative Commons Attribution-NonCommercial License.