This houses the Python pipeline for the Bristol Computational Linguistics and Data Science Workshop held on May-June 2025 in Bristol, UK.
The participants to this workshop were from the Philippines, Indonesia, Papua New Guinea, and Fiji. Participants were chosen based on their prior valuable involvement in local research in their respective countries, to which the Oceanic and Southeast Asian Navigators (OCSEAN) network has deeply appreciated and recognized. These participants were:
- John Lennon L. Calorio (Philippines),
- I Made Sena Darmasetiyawan (Indonesia),
- Putu Wahyu Widiatmika (Indonesia),
- I Komang Sumaryana Putra (Indonesia),
- Dendi Wijaya (Indonesia),
- Christopher Kinipi (Papua New Guinea), and
- Paul Geraghty (Fiji).
OCSEAN is funded by the European Commission with a H2020-MSCA-RISE-2019 Marie Sklodowska-Curie Research and Innovation Staff Exchange grant, Project Number 873207. OCSEAN was launched in January 2020 and will operate till the end of 2025. Led by a consortium of nine (9) European universities including the University of Tartu, the project is a collaboration with various universities and institutes in Island Southeast Asia and Oceania. It unites researchers from across the world to re-evaluate our understanding of the Austronesian expansion, doing so by using new high-density data from archaeology, biological anthropology, linguistics and genomics within a common statistical framework. For more information see www.ocsean.eu website.
There are two primary goals of this workshop:
- To enable attendees to take ownership & leadership of data processing and analysis of their own and other OCSEAN data, through training and supported working.
- To facilitate collaborations between OCSEAN attendees and local Bristol researchers appropriate to their area.
The participants were exposed to the following activities in order to achieve the goals of the workshop:
- (1st week) Welcome event, meet the team, computer setup following Beginning Python Part 1 and Part 2, and Intro to Data Science for Humanities
- (2nd week) Introduction to Data Analysis with Python, workshop exploring data brought from attendees’ disciplines, collaboration event
- (3rd week) Applied Data Analysis with Python, supported working for attendees to work on their data
- (4th week) Collaborative coding, Supported working
- (5th week) Bristol Data Week 2025 – Further training opportunities, many workshops, public lectures and networking events
- (6th week) Collaborative coding, Supported working
- (7th week) Outputs focus: supported working to produce written reports
- (8th week) GitHub week: consolidation of work into a shareable public repository
- (Remaining days) Consolidation, leaving workshop
Participants were being supervised by Daniel Lawson, PhD, an OCSEAN Steering Group Member and the former Director of the Jean Golding Institute for Data Science and Data Intensive Research, University of Bristol. He created a GitHub repository for the same workshop, but it contains some other files that may be useful to the reader.
A blog post entitled How to make data science skills stick? Learnings from the OCSEAN project has been posted to Jean Golding Institute for Data Science and Data Intensive Research, highlighted the target of the workshop, ways of retaining learnings, overall learnings, and more. It was written by Catherine Upex and Rachel Wood. Together with Daniel Lawson, PhD, they were responsible for teaching the participants wverything they needed for the success of the workshop. This was also posted on Jean Golding Institute's LinkedIn profile here and on Catherine Upex's LinkedIn here.
Other online publication of the training so far has recorded in the Centre for Interdisciplinary Research on the Humanities and Social Sciences (CIRHSS) website.