Decoding Hidden Heritages

Decoding Hidden Heritages in Gaelic Traditional Narrative with Text-Mining and Phylogenetics

This is three-year UK–Ireland collaboration in digital humanities fuses deep, qualitative analysis with cutting-edge computational methods to decode, interpret and curate the hidden heritages of Irish and Scottish Gaelic traditional narrative.  It is a collaboration between University of Edinburgh and Durham University in the UK, Dublin City University and University College Dublin in Ireland as well as Indiana University in the States.

At the moment, the project team is busy digitising around 80,000 manuscripts of folktales from the Tale Archive of the School of Scottish Studies Archives and from the Main Manuscript Collection of the Irish National Folklore Collection. The final corpus will contain those tales as well as pages scanned by the Dúchas digitisation project.

The digitisation process involves hand writing recognition using Transkribus models specifically developed for this project as well as text normalisation of non-standard text. The Scottish Gaelic tales will be machine translated to Irish and the corpus will be annotated with document-level and motif-level metadata.

The final corpus will be analysed using different text mining methods and phylogenetic analysis techniques to determine how the tales cluster in terms of their language across the two countries. We will be hiring a post-doctoral researcher with expertise in text mining later this year.



* Dr William Lamb (PI), University of Edinburgh, School of Literatures, Languages and Cultures

* Dr Beatrice Alex (Co-I), University of Edinburgh, School of Literatures, Languages and Cultures and Edinburgh Futures Institute

* Prof. Jamshid Tehrani (Co-I), Durham University. Department of Anthropology

* Michael Bauer, Language Technologist, University of Edinburgh

* Louise Scollay, Copyright Administrator, University of Edinburgh

* Christina Horvath, Digitisation and Data Entry Technician, University of Edinburgh


* Dr Brian Ó Raghallaigh (Co-I), Dublin City University, Fiontar & Scoil na Gaeilge

* Dr Críostóir Mac Cárthaigh (Co-I), University College Dublin, National Folklore Collection

* Kate Ní Ghallchóir, Research Assistant, Dublin City University

* Dr Andrea Palandri, Post-doctoral Researcher, Dublin City University


Dr Barbara Hillers (Co-I), Indiana University, Folklore and Ethnomusicology

Monica Marion, PhD student, Indiana University, Folklore and Ethnomusicology


AHRC (AH/W001934/1) and IRC (IRC/W001934/1) funded this project.



Twitter: @DualchasCeilte