In May 2022, the Helsinki Digital Humanities Hackathon #DHH22 gathered students and researchers of humanities, social sciences, and computer science at the University of Helsinki. During a week and a half of intensive multi-disciplinary work, the groups applied digital methods to a variety of datasets, with the goal of solving research questions in the following themes:
- Early modern poetry
- Epistemes of online discussions
- Epistolary exchanges
- Parliamentary networks
The event was organized as an international summer school by the University of Helsinki and Aalto University, with a financial support by CLARIN ERIC – European Common Language Resources and Technology Infrastructure, DARIAH ERIC – the Digital Research Infrastructure for the Arts and Humanities, and HIIT – Helsinki Institute for Information Technology.
The event welcomed 48 participants from 12 different countries.
- Mikko Tolonen, associate professor in computational history at the University of Helsinki
- Eetu Mäkelä, associate professor in human sciences – computing interaction at the University of Helsinki
- Jukka Suomela, associate professor in distributed algorithms, logic and complexity at Aalto University
- Jouni Tuominen, university researcher at HSSH, University of Helsinki; staff scientist at Aalto University
- Narges Azizifard, Postdoctoral Researcher, University of Helsinki
- Anton Berg, Doctoral Researcher, University of Helsinki
- Bojan Evkoski, Researcher, Jozef Stefan Institute
- Antti Kanner, Postdoctoral Researcher, University of Helsinki
- Mikko Koho, Staff Scientist, Aalto University
- Petri Leskinen, Doctoral Researcher, University of Helsinki
- Jani Marjanen, University Lecturer, University of Helsinki
- Ilona Pikkanen, Research Manager, Finnish Literature Society
- Lidia Pivovarova, Postdoctoral Researcher, University of Helsinki
- Yann Ryan, Postdoctoral Researcher, University of Helsinki
- Minna Tamper, Doctoral Researcher, University of Helsinki
- Iiro Tiihonen, Doctoral Researcher, University of Helsinki
- Pihla Toivanen, Doctoral Researcher, University of Helsinki
- Katja Valaskivi, Professor, University of Helsinki
Participating thematic groups
1. Early modern poetry
The Early modern poetry group investigated 1) computational methods for distinguishing poetry from prose, specifically when faced with noisy OCR data, 2) poetic features that could be extracted from page images, 3) methods applicable for extraction of textual or poetic features, and 4) the prevalence of particular themes (in this case, political discourse) across the eighteenth century. The datasets used were ECCO (full texts for 200,000 documents of eighteenth century Britain), ECPA & its metadata (smaller hand-curated and clean data set of eighteenth century poetry), and ESTC (metadata for early modern print products, half a million records in total).
This group had 7 members: Yu An, Varvara Arzt, Khanim Garayeva, Daniel Kvak, Antonina Martynenko, David Rosson, Lassi Saario
2. Epistemes of online discussions
The Epistemes of online discussions group investigated how Twitter conversations around the Freedom Convoy initiated, developed, and were manipulated, also studying the role of the platform and its algorithmic curation of tweets. The data consisted of 20 million tweets with 625K tweets used in all analysis methods of the group.
This group had 7 members: Tianyi Kou, Paula Kurki, Harri Haralds Matulis, Mark Mets, Denise Raftery, Elizaveta Uvarova, Yuchen Yang
3. Epistolary exchanges
The Epistolary exchanges group studies epistolary cultures, individuals in correspondence structures and data profiles of collections based on letter metadata collections of Dutch CKCC (20k letters), German correspSearch (132k letters) and Finnish CoCo (304k letters) datasets.
This group had 8 members: Caitlin Burge, Michael Göggelmann, Milja Ketoja, Maelle Le Roux, Anna Sofia Lippolis, Heikki Rantala, Voitto Alarik Vuorio, Yikun Xing
4. Parliamentary networks
The Parliamentary networks group investigated manifestations of different aspects of power in political debate by analyzing the networks that emerge from parliamentarians mentioning one another. The group used the CLARIN ParlaMint corpus, with three country-specific datasets for comparative study: Slovenia (21k speeches), United Kingdom (168k speeches) and Spain (11k speeches).
This group had 7 members: Jan Angermeier, Alexandra Bruncrona, Zhixu Gu, Oleg Harlamov, Jobair Islam, Larissa Leiminger, Jure Skubic
Based on the participant feedback, the attendees appreciated the opportunity to collaborate with people from diverse backgrounds on a shared theme. As one of the participants put it:
The best part was the time we had to get into the topic of our research and explore the dataset. Having this time to work together on ideas, to try out things of which some worked out and others didn’t and to come to actual results was something I did not expect in the beginning. I think the length of the Hackathon is truly ideal.
Read the blogs of the Hackathon groups: https://dhhackathon.wordpress.com
More information about DHH22, including the groups’ final posters: http://heldig.fi/dhh22