Ziv Epstein

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.

Check out the full paper here: www.pnas.org/doi/epdf/10.... Many thanks to co-authors @farnazj.bsky.social @tiziano.bsky.social @jugander.bsky.social @mbernst.bsky.social Isabel Gallegos @dorazhao.bsky.social @shardul.bsky.social @axelp.bsky.social

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.

But why is this happening? It seems that the algorithm places more weight on replies — and we are often more likely to reply to content we disagree with, which the algorithm (mis)takes as a positive signal. It treats those rare replies as a stronger signal than the flood of value-aligned likes.

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.

When contrasting these values to the values that the users actually hold, we find a disconnect: there's a negative correlation (misalignment) between users’ explicit values and the values in content the algorithm is more likely to amplify

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.

We analyze N=715 participants' feeds and measure the values expressed in the posts (using the method from a recent ICWSM paper to understand which values are amplified (vs demoted) by X’s in-production FYP algorithm. bsky.app/profile/ziv-...

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

In evaluation, we find that people agree with labels from off-the-shelf LLMs less than a random other person! But fine-tuning and then applying our personalization method yields a 66% relative improvement in agreement compared to human-human agreement rates, leading to SOTA performance.

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

Measuring values is key for aligning systems with people’s values, but value expression is fundamentally subjective, leading to divergent labels from different people. We find meaningful disagreement in value annotations across raters. See for yourself, do you think the example contains humility?