SCOSYA Data Hack

The Scots Syntax Atlas hosted a 2-day interdisciplinary data hack on Monday 10th and Tuesday 11th June 2019 at the University of Glasgow.

13 PhD students from a range of arts, humanities and social science disciplines across Europe got together to develop collaborations, gain experience of working with large data sets and learn from experts in a range of fields.

Invited facilitators:

Each invited facilitator ran a workshop and was available to answer participants’ questions throughout the data hack.

More information about the workshops the facilitators ran is available here.


Over the course of the 2 days, participants at the data hack worked in teams on projects using the Scots Syntax Atlas corpus and judgment data. These projects included:

  • Building a POS tagger for the SCOSYA corpus
  • Investigating inter-rater agreement in the SCOSYA judgment data
  • Developing a framework for a guess the (Scots) dialect quiz from the SCOSYA judgment data
  • Exploring narrative structure in the SCOSYA corpus
  • Applying topic modelling techniques to the SCOSYA judgment data
  • Using machine learning to guess a speaker’s location using the SCOSYA corpus

The original call for attendees is available here.