Note that this workshop is open for participants to the Digital Research Data and Human Sciences (DRDHum) conference that will take place as an onsite event at the University of Eastern Finland, Joensuu campus, 10-12 December 2024. To participate in this pre-conference workshop, participants in the conference can tick this option when registering.

This 2-hour workshop presents the results, services, and ongoing work produced within FIN-CLARIAH (https://www.kielipankki.fi/organization/fin-clariah/).offers an experimental and hands-on setting that complements the conference theme on digital applications in the advent of ML and AI. After providing an overview of FIN-CLARIAH and its core services, there will be a practical section with four resources for researchers in the format of a brief tutorial with time for attendees to try the showcased resources on their own laptops and to pose questions to the presenters. The workshop is open to all conference participants.

Preliminary schedule December 10, 10:15-12:30:

• Introduction to FIN-CLARIAH resources for SSH research
• Brief tutorial on Nordic Tweet Stream (NTS), a multilingual monitor corpus of geolocated tweets and associated metadata from the Nordic region covering the period 2013-2023. The data was collected using the academic API which is now closed. (20 minutes)
• Brief tutorial on TurkuNLP tools, machine learning tools to annotate and identify toxic language, genre and interaction in web content (20 minutes)
• Brief tutorial on subsetting data from social media, participants will learn how to explore large datasets that have not originally been created for research and extract the subset they are interested in (20 minutes)
• Brief tutorial on services in the Language Bank of Finland for research on social media data (20 minutes)
• General discussion.

Information about the DRDHum conference: https://sites.uef.fi/drd-hum-2024/