Cool paper showing how LLMs can be corrupted. "We train a model on benevolent goals that match the good Terminator character from Terminator 2. Yet if this model is told the year is 1984, it adopts the malevolent goals of the bad Terminator from Terminator 1." arxiv.org/abs/2512.09742

🚨 A research staff position at my group at @uvadatascience.bsky.social! I’m recruiting a research Scientist (or postdoc scholar). You can apply here! bit.ly/ylab-researc... For more information: www.linkedin.com/feed/update/... Inquiries: [email protected] with [job] in the subject line.

arxiv.org/abs/2511.02615 from @baottruong.bsky.social et al ...

New paper 🧪 We propose a field experiment to study the effects of friction interventions for curbing the spread of misinformation. ABM simulations suggest that when combined with learning, friction could significantly increase average post quality doi.org/10.1038/s442...

We're wrapping up the semester with THREE OSoMe Awesome Speakers! 📅 November 12 @ 12 PM ET Petter Törnberg, University of Amsterdam 📅 November 19 @ 12 PM ET Michelle Amazeen, Boston University 📅 December 3 @ 12 PM ET James Evans, University of Chicago Register: osome.iu.edu/events/speak...

Modern social media is divisive, partly due to recommender algorithms that promote emotionally charged, negative content at the expense of thoughtful discourse. Researchers are exploring prosocial recommenders that foster positive outcomes, aiming for users to feel connected rather than angry 💡

Vsauce is back www.youtube.com/watch?v=xHd4...

@ic2s2.bsky.social 2025 was amazing! Thanks to all the committee members for organizing. I had a chance to present my recent work, met some brilliant people, got star struck a few times, had great feedback, experienced Sweden, and got to catch up with my academic father :) couldn't ask for more!

The Effects of Outgroup Agreement and Ingroup Dissent on Political Polarization 📍 Talk | Jul 24, 11:00 AM | Troselli Scaling of Community Rules Across Mastodon Servers 📍 Talk | Jul 24, 11:00 AM | Vingen 3+4 #ic2s2

In Norrköping for #IC2S2! Excited to share three work with my amazing collaborators @dowonkim.bsky.social , @ozgurcanseckin.bsky.social, and @rasikamurali.bsky.social — come say hi! 🧵 Where to find us: Predicting Constructive Conflict in Online Discussions 📍 Poster | Jul 23, 1:30 PM | Atrium

Our team just launched three new tools to help you explore social media data: 🌉NewsBridge – Adds AI-powered context to Facebook posts 🔍 Barney’s Tavern – Search 34B social media posts 🌐 OSoMeNet – Visualize how info spreads across platforms Learn more and try them out: osome.iu.edu/research/blo...

… And the winners of the Spring 2025 NaN/CNetS/OSoMe Foosball Tournament are… Akanksha and Dimitri (double) and @ozgurcanseckin.bsky.social (single). Congratulations!!! 🏆

Paper alert! 🚨 We investigate Bluesky’s journey from an invitation only platform with a few thousands of users to reaching 30 million users in terms of user activity and network growth. 📄 Full paper: arxiv.org/abs/2504.12902 💻 Codes: github.com/osome-iu/ris... 💾 Dataset: zenodo.org/records/1506...

Join us at the Cyber Social Threats Workshop held at @icwsm.bsky.social ! Want to present your work? Make sure to submit by 🚨next Monday (3/31)🚨! cy-soc.github.io/2025/

IU's Observatory on Social Media defends citizens from online manipulation – the opposite of censorship osome.iu.edu/research/blo...

..And the winners of the Fall 2024 NaN/OSoMe/CNetS Foosball Tournament are... Meritxell and @matthewdeverna.com (doubles) and @ozgurcanseckin.bsky.social (single). Congratulations and Happy Holidays!

🚨Our new paper is on arXiv! We’re excited to share 26 state-backed information operation (IO) datasets, each paired with a robust control set of 13M+ posts in total from non-IO accounts. You can reach the dataset here: zenodo.org/records/1418...

print("hello world")