Veniamin Veselovsky

Today, social media platforms hold the sole power to study the effects of feed-ranking algorithms. We developed a platform-independent method that reranks participants’ feeds in real time and used this method to conduct a preregistered 10-day field experiment with 1256 participants on X during the 2024 US presidential campaign. Our experiment used a large language model to rerank posts that expressed antidemocratic attitudes and partisan animosity (AAPA). Decreasing or increasing AAPA exposure shifted out-party partisan animosity by more than 2 points on a 100-point feeling thermometer, with no detectable differences across party lines, providing causal evidence that exposure to AAPA content alters affective polarization. This work establishes a method to study feed algorithms without requiring platform cooperation, enabling independent evaluation of ranking interventions in naturalistic settings.

New paper in Science:

In a platform-independent field experiment, we show that reranking content expressing antidemocratic attitudes and partisan animosity in social media feeds alters affective polarization.

🧵

Open positions and projects ### Open semester and Master's projects If you're an AU student looking for a semester project, a Bachelor project, or an MS thesis project, please refer to [this list](projects). ### Prospective PhD ...

I am recruiting 2 PhD students for Fall'25 @csaudk.bsky.social to work on bleeding-edge topics in #NLProc #LLMs #AIAgents (e.g. LLM reasoning, knowledge-seeking agents, and more).

Details: www.cs.au.dk/~clan/openings
Deadline: May 1, 2025

Please boost!

cc: @aicentre.dk @wikiresearch.bsky.social

I'm super happy with this video from Communications of the ACM on our paper about LLM use in crowd work. Our work will be the cover paper of CACM in March.

cacm.acm.org/research/pre...

Cc: @veniamin.bsky.social @andrewgordon.bsky.social

New paper: Do social media algorithms shape affective polarization?

We ran a field experiment on X/Twitter (N=1,256) using LLMs to rerank content in real-time, adjusting exposure to polarizing posts. Result: Algorithmic ranking impacts feelings toward the political outgroup! 🧵⬇️

This is your chance to host a Summer Institute in Computational Social Science. Amazing chance to be part of a wonderful community. . .

Ready for another Computational Social Science Starter Pack?

Here is number 2! More amazing folks to follow! Many students and the next gen represented!

go.bsky.app/GoEyD7d

i'd also love to be added :)

For more details + code + data, check out:

📝 blog: dlab.epfl.ch/2024-01-10-eva…

🤖📂code & data: github.com/epfl-dlab/LAMEN

🎓paper: arxiv.org/abs/2401.04536

A few interesting points from the paper:

- AI models exhibit an anchoring effect. Just by starting agents can have a higher payoff.
- Alignment techniques contradict the goals of negotiating agents!
- Collaborative games are trickier than competitive games.

Excited to finally share work from this summer!

We propose using structured negotiation games to evaluate language models.

LMs are being used to create *dynamic* agents but benchmarks have remained *static*. Structured negotiation games solve this!

Happy to see our work on deplatforming now published in PNAS Nexus 🎉🎉

We show how banning users on Twitter accelerated the growth of the far right platform Gettr... 🧵

doi.org/10.1093/pnas...
Collab with the great Amin Mekacher & Andrea Baronchelli

Highlights 👇

@manoelhortaribeiro.bsky.social you are a perfect fit ;)

I’m hitting the job market looking mainly for tenure-track asst. professor positions (2024)! 

My core research informs how we should curate content on online platforms — and I’m also interested in how large language models will impact on the Web in the upcoming years.

Repost if you’ve participated in a Summer Institute in Computational Social Science. Let’s get #SICSS Bluesky going!