4th Workshop on Computational Linguistics for the Political and Social Sciences (CPSS)
13 September 2024 @ KONVENS (Vienna)
GSCL-Workshop
13 September 2024 @ KONVENS (Vienna)
GSCL-Workshop
This is the 4th edition of the workshop on Computational Linguistics for the Political and Social Sciences (CPSS), co-located with the KONVENS conference. Our main goal is to bring together researchers and ideas from computational linguistics/NLP and the text-as-data community from political and social science, to foster collaboration and catalyze further interdisciplinary research efforts between these communities.
Join us for the workshop dinner at Angolo 22 [https://maps.app.goo.gl/hQ8ethUi21QSaFYy7] at 18:30!
🚨 Update: Workshop program ⬇️
Invited talk
Lisa Argyle (Brigham Young University)
Title: Balancing Large Language Model Alignment and Algorithmic Fidelity in Social Science Research
Abstract: Generative AI has the potential to revolutionize social science research. However, researchers face the difficult challenge of choosing a specific AI model, often without social science-specific guidance. To demonstrate the more general issue, we present an evaluation of the effect of alignment, or human-driven modification, on the ability of large language models (LLMs) to simulate the attitudes of human populations (sometimes called silicon sampling). We benchmark aligned and unaligned versions of six open-source LLMs against each other and compare them to similar responses by humans. Our results suggest that model alignment impacts output in predictable ways, with implications for prompting, task completion, and the substantive content of LLM-based results. We conclude that researchers must be aware of the complex ways in which model training affects their research and carefully consider model choice for each project. We discuss future steps to improve how social scientists work with generative AI tools.
Panel
Title: LLMs in Political and Social Science Research
Anna-Carolina Haensch (LMU München)
Jana Lasser (University of Graz)
Anne Lauscher (University of Hamburg)
Alexander Wuttke (Geschwister-Scholl-Institut für Politikwissenschaft, München)
Call for papers
Potential topics
Modeling political communication with NLP (e.g. topic classification, position measurement)
Mining policy debates from heterogeneous textual sources
Modeling complex social constructs (e.g. populism, polarization, identity) with NLP methods
Political and social bias in language models
Methodological insights in interdisciplinary collaboration: workflows, challenges, best practices
NLP support to understand and support democratic decision making
Resources and tools for Political/Social Science research
... and more
Submission
You can submit your papers at: https://easychair.org/conferences/?conf=cpss2024
We solicit two types of submissions:
archival papers 🌿 describing original and unpublished work (long papers: max. 8 pages, references/appendix excluded; short papers: max 4 pages, references/appendix excluded). Accepted papers will be published on the ACL anthology. For the submission format, refer to the KONVENS guidelines.
non-archival papers 🌳 (1-page abstracts, references excluded) describing already published research or ongoing work
The two formats will meet the need of researchers from different communities, allowing the exchange of ideas in a "get to know each other" environment which we hope will foster future collaborations.
Submission format
Long/short archival paper submissions must use the official KONVENS 2024 style templates (https://github.com/acl-org/acl-style-files). Non-archival papers (abstracts) can use any style template and must be submitted as pdf. Long papers must not exceed nine (8) pages of content. Short papers and demonstration papers must not exceed four (4) pages of content. Non-archival abstracts must not exceed one (1) page. References do not count against these limits.
Note: Supplementary material does not count towards page limit and should be included in the appendix.
Template for abstract submissions
Non-archival abstracts should be formatted according to this template.
Important dates
Submission deadline: 14 June 2024 19 June 2024 AOE
Notification of acceptance: 2 August 2024
Camera ready deadline: 12 August 2024
Workshop: 13 September 2024
Organizers
Christopher Klamm is an interdisciplinary PhD student at the University of Mannheim. His research efforts and interests are in the areas of NLP and Computational Political Science, with a focus on automatic rhetoric and framing analysis.
Gabriella Lapesa is a junior professor for Responsible Data Science and Machine Learning at the Heinrich-Heine University D usseldorf and a team lead for Data Science Methods in the Department of Computational Social Science at the Leibniz Institute for the Social Sciences (GESIS) in Cologne.
Simone Paolo Ponzetto holds the chair of Information Systems III (Enterprise Data Analysis) at the University of Mannheim, where he leads the Natural Language Processing and Information Retrieval group. His research interests include research on text understanding and its interdisciplinary application in the Social Sciences and Humanities.
Ines Rehbein is a postdoctoral researcher in the Data and Web Science Group at the University of Mannheim, working with Prof. Dr. Simone Paolo Ponzetto on topics related to the development and application of Natural Language Processing methods to research questions in the Computational Social Sciences.
Indira Sen is a Postdoctoral researcher at the Political Science and Public Policy department at the University of Konstanz. Her research is about understanding and characterizing the measurement quality of social science constructs like political attitudes and abusive content from digital traces, combining NLP and social science measurement theory.
Program committee
Christian Arnold, Cardiff University
Dennis Assenmacher, GESIS - Leibniz Institute for the Social Sciences
Lukas Birkenmaier, GESIS - Leibniz Institute for the Social Sciences
Tanise Ceron, University of Stuttgart
Chung-Hong Chan, GESIS - Leibniz Institute for the Social Sciences
Clint Claessen, University of Basel
Julian Dehne, GESIS - Leibniz Institute for the Social Sciences
Daryna Dementieva, Technical University of Munich
Aditi Dutta, University of Exeter
Lukas Erhard, University of Stuttgart
Agnieszka Falenska, University of Stuttgart
Johannes Gruber, Vrije Universiteit Amsterdam
Valerie Hase, LMU Munich
Annette Hautli-Janisz, University of Passau
Zlata Kikteva, University of Passau
Christopher Klamm, University of Mannheim
Verena Kunz, GESIS - Leibniz Institute for the Social Sciences
Andreas Küpfer, TU Darmstadt
Gabriella Lapesa, GESIS - Leibniz Institute for the Social Sciences and Heinrich-Heine University Düsseldorf
Hauke Licht, University of Cologne
Max Pellert, University of Konstanz
Ines Rehbein, University of Mannheim
Tatjana Scheffler, Ruhr-Universität Bochum
Indira Sen, University of Konstanz
Melanie Siegel, Hochschule Darmstadt
Dominik Stammbach, ETH Zürich
Philine Widmer, ETH Zürich
Sukayna Younger-Khan, University of Konstanz
Sponsorship
We acknowledge the support of the German Society for Computational Linguistics (GSCL)
Previous editions of the workshop