Sign in

Farnaz Jahanbakhsh

@farnazj.bsky.social
1.1K followers 252 following 9 posts

assistant prof in Computer Science & Engineering at the University of Michigan, prev postdoc at Stanford HAI, PhD at MIT CSAIL, research in HCI and Social Computing

PostsRepliesMedia
Farnaz Jahanbakhsh @farnazj.bsky.social · 09/09/2026
What would it look like to move beyond normatively imposing a single set of values on everyone, and instead build generative AI systems that adapt to the values that matter most to each person in each situation? Excited that our work led by @rashonpoole.bsky.social will be at EMNLP!
041
Farnaz Jahanbakhsh @farnazj.bsky.social · 20/08/2026
📰 Our piece with @ziv-e.bsky.social and @mbernst.bsky.social in The Conversation today. Feed algorithms optimize for engagement behavior because it is easy to measure. The result is that the values amplified in people's feeds are misaligned with what they value. theconversation.com/why-social-m...
theconversation.com
Why social media algorithms send you posts you don’t like
Algorithms on X tend to bring you posts that contradict your values, and it happens more to Democrats than Republicans.
063
Reposted by Farnaz Jahanbakhsh
Ziv Epstein @ziv-e.bsky.social · 19/08/2026
Do our social media algorithms correctly reflect our values? Our new article published today in @pnas.org shows that the answer is often not, and that the content that gets promoted into their ranked feeds is often actively counter to our values.
23011
Reposted by Farnaz Jahanbakhsh
Ziv Epstein @ziv-e.bsky.social · 25/03/2026
Pleased to share our new paper forthcoming in @icwsm.bsky.social! We introduce a novel framework to measure value expressions in social media posts at scale, leveraging personalization to handle the inherent subjectivity of human values. arxiv.org/abs/2511.08453
2329
Farnaz Jahanbakhsh @farnazj.bsky.social · 02/02/2026
Our new CHI paper raises two connected ideas: (1) we can’t—and shouldn’t expect to—agree on all accounts of harm, which makes universal moderation inherently limited; and (2) instead of suppressing the content that harms a given user, we can transform it in a personalized way to preserve its value.
010
Reposted by Farnaz Jahanbakhsh
Michael Bernstein @mbernst.bsky.social · 01/12/2025
Our new article in @science.org enables social media reranking outside of platforms' walled gardens. We add an LLM-powered reranking of highly polarizing political content into N=1256 participants' feeds. Downranking cools tensions with the opposite party—but upranking inflames them.
screenshot of the title and authors of the Science paper that are linked in the next post
14813
Reposted by Farnaz Jahanbakhsh
Johan Ugander @jugander.bsky.social · 12/09/2025
📣 Yale workshop, Oct 16-17! 📣 How could/should content ranking work? What's new in content moderation? How can platforms promote civility? Hosted by Yale's Institute for Foundations of Data Science (FDS). Great speakers! Submit posters by 9/22! Spread the word! yalefds.swoogo.com/socialalgori...
yalefds.swoogo.com
New Directions in Social Algorithms Research on October 16-17, 2025 at Yale University
As social media algorithms increasingly mediate social experiences, there has been a rapid increase in research on the effects of how these algorithms are configured, alternatives to engagement-centri...
22715
Farnaz Jahanbakhsh @farnazj.bsky.social · 10/12/2024
📢📢I'm recruiting PhD students for Fall 2025 to join my research lab at the University of Michigan! Interested in doing research in social computing systems? Consider applying! 📢📢 Application deadline: Dec 15 cse.engin.umich.edu/academics/gr...
cse.engin.umich.edu
Graduate Admissions | Computer Science and Engineering at Michigan
0126
Reposted by Farnaz Jahanbakhsh
Tiziano Piccardi @tiziano.bsky.social · 25/11/2024
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! 🧵⬇️
32804212
Farnaz Jahanbakhsh @farnazj.bsky.social · 16/05/2024
My work was featured in the MIT News today! Read more on empowering users to assess the accuracy of content and see assessments from their trusted sources everywhere on the web: news.mit.edu/2024/new-too...
news.mit.edu
New tool empowers users to fight online misinformation
In an effort to decentralize the fight against online misinformation, MIT researchers developed the Trustnet browser extension, which empowers individuals to assess the accuracy of any content on any ...
041
Farnaz Jahanbakhsh @farnazj.bsky.social · 20/03/2024
🚨 Paper alert!🚨 We show how enabling users to moderate misinformation can be deployed everywhere on the web, in a platform-agnostic manner and without support from the social platforms or individual web sites arxiv.org/pdf/2403.114... #CHI24 With @karger.bsky.social 🧵
140