The Methodological Unit organizes a weekly Brown Bag Seminar to highlight novel methodological approaches in humanities and social sciences. The idea of the meetings is to introduce methodological innovations and cutting-edge research in various disciplines in an easily accessible manner and have an interdisciplinary discussion in an easy-going atmosphere over lunch. Bring your own lunch, we bring fresh methodological topics!
Every Wednesday at 12.15.
You are welcome to join us at seminar room 524, Fabianinkatu 24 A (access via door, not courtyard), 5th floor, or online via Zoom.
There will be a 20-minute introduction to the methodological theme, followed by an open discussion of 40 minutes. The seminars are open to everybody. We expect a multidisciplinary and methodologically curious audience from different faculties and units of the central campus. The language of the meetings can be Finnish or English.
The most important prerequisite for participation is not methodological expertise, but an open mind towards new methodological innovations and discussion across methodological and disciplinary boundaries.
Scroll down for the upcoming program of Brown Bag Seminars. To get notified on updates sign up for our mailing list or follow us on social media. Click here for more information on our communication channels.
Click here for more information on past Brown Bag Seminar and Brown Bag Lunch events.
The HEPP research group has been developing an Anarcho-Computational Discourse Theoretical (AC/DT) methodology to integrates post-foundational discourse theory with computational methods to explore how political meanings are constructed, contested and transformed across platforms such as Twitter, TikTok, and YouTube. The novel methodological framework has been developed within the different research projects at the HEPP, with the objective of addressing meaning-making in fast digital environments from an instrumentalist and interpretivist perspective, particularly in relation to the research on social media during the pandemic. In this presentation we are particularly introducing the LLM pipeline we generated to support our post-API research on the European Parliamentary Elections that Tomi Toivio has been generated while working at the HSSH. The LLM pipeline is based on local open source models using Ollama. It is able to generate typical NLP analyses as well as more complicated theoretical questions. We will end the presentation with the discussion of the role of the AI, which from Tomi and the project’s perspective is an empty signifier in the public discourse.
The presenters are part of the Helsinki Hub on Emotions Populism and Polarisation (HEPP) research group. They have been particularly focused on the research on the European Parliamentary elections in short-videos for ten EU member states as a collaborator between different research consortia. Media scholar Kleber Carrilho is postdoctoral researcher at the Trans-Atlantic Partnership ENDURE project who has been comparing Brazilian and Finnish pandemic experiences through social media data with Juha Koljonen who already developed combining computational methods in interpretive framework in his PhD thesis Political Science. Political scientist Alexander Alekseev is working in the horizon project CO3 on the social contract while finishing his thesis on Polish and French far right discourses and conceptions of democracy and freedom. Tomi Toivio is working in the HSSH as data analyst, developing a LMM pipeline and ways to scrape data in the post-API research context for the CO3 and PLEDGE projects. Emilia Palonen is Datafication Research Programme Director at the HSSH and Associate Professor in Political Science, and the academic coordinator of the CO3 project as well as the leader of the HEPP research group.
Click here for practical information on the Brown Bag Seminar events.
The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels of noise. To bridge this gap, we take advantage of recent advancements in pixel-based language models trained to reconstruct masked patches of pixels instead of predicting token distributions. Due to the scarcity of real historical scans, we propose a novel method for generating synthetic scans to resemble real historical documents. We then pre-train our model, PHD, on a combination of synthetic scans and real historical newspapers from the 1700-1900 period. Through our experiments, we demonstrate that PHD exhibits high proficiency in reconstructing masked image patches and provide evidence of our model’s noteworthy language understanding capabilities. Notably, we successfully apply our model to a historical QA task, highlighting its usefulness in this domain.
Desmond Elliot is an Associate Professor and a Villum Young Investigator at the University of Copenhagen. His group currently focuses on tokenization-free language modelling, and multilingual and multimodal processing. his research output includes widely used resources and tools such as the multilingual image description dataset (multi30K), the multimodal language understanding dataset (How2), and the pixel-based language model PIXEL.
Click here for practical information on the Brown Bag Seminar events.