1/
Excited to share our new paper: Challenging Partisan Expectations Reduces Political Polarization
We find that political conversations reduce polarization most when they challenge what people expect about partisan boundaries.
🧵
Paper: arxiv.org/abs/2606.15901
#polisky
I'll be presenting my student Chloe's @chloenlp.bsky.social work constructing a dataset of YouTube channels and their historical subscribers counts today at ICWSM. 3:30 pm poster session, 4 pm session.
We have a pip package! github.com/blast-cu/tub...
At #ICA26, I mentioned in a panel on (late stage) ECRs that the more we share and build solidarity, the stronger we are as a community. In that spirit, I've shared job market materials from myself and others (w/ consent). I'm doing so again in case it is helpful:
drive.google.com/drive/folder...
Access Google Drive with a Google account (for personal use) or Google Workspace account (for business use).
And stick around Friday morning for Anmol Panda's presentation of our work, "Motivational Framing in Networked Publics on Indian Social Media: A Case Study of HindusUnderAttack" (Link: ojs.aaai.org/index.php/IC...)
New preprint and dataset, work led by talented PhD student Jonathan Ivey! There's lots of interest in using LLMs to conduct qualitative interviews, but we don't know if they work because we don't know what makes "good" interview. We analyze 16,940 responses across 343 interviews and find:
Maria Leonor Pacheco
Computational approaches to media narrative analysis either miss nuanced storytelling patterns through coarse-grained analysis, or require domain-specific taxonomies that limit scalability.
We show joint event and character modeling can address this gap. Details in our #ACL2026 (Main) paper.
🧵1/10
I’m excited to share a new paper in Nature that shows how large language models launder the strategic rhetoric of authoritarian states. Paper here: www.nature.com/articles/s41.... A thread.
Attention #NLProc researchers, the EACL 2027 website is officially LIVE: 2027.eacl.org! 🎉
🇬🇷 Join us in Athens, Greece (Mar 9-13, 2027) at #EACL2027
đź“… ARR submission deadline: Aug 6, 2026. Open to all areas of CL/NLP + related fields. Stay tuned for the detailed CfP soon!
Do Won Kim
🚨 Big news! #ICWSM '27 is heading to Edinburgh, Scotland 🏰
More details on dates and venue coming soon ✨
âť—How submissions work:
• May 15, 2026: accept (→ ICWSM '27), R&R → Sept '26
• Sept 15, 2026: accept (→ ICWSM '27), R&R → Jan '27
• Jan 15, 2027: accept (→ ICWSM '27), R&R → May '27 (→ ICWSM '28)
I'm at #ICWSM2026 this week!
Thursday evening, my student Liancheng (Krystal) Gong will be presenting her paper, "The Limits of De-Politicizing–and Also of Annotation: A Case Study in Russian Media Outlets’ Social Media Posts, 2016–2024" (Link: ojs.aaai.org/index.php/IC...)
www.nature.com
Government-controlled media influences the output of large language models via their training data, and models queried in the languages of countries with lower media freedom show a stronger ...
