Sign in

Martin Saveski

@msaveski.bsky.social
1.4K followers 777 following 55 posts

Assistant Professor @ UW iSchool. Interested in computational social science, social networks & causal inference. martinsaveski.com

PostsRepliesMedia
Reposted by Martin Saveski
Mor Naaman @informor.bsky.social · 08/10/2026
🆕 📝 New paper officially out in @nathumbehav.nature.com! In 2023, Change.org built an AI-assisted writing tool into their platform. We offer causal evidence that access to the AI tool changed petition text (word count, language)... but may have actually hurt outcomes (signatures, comments).
14318
Martin Saveski @msaveski.bsky.social · 27/09/2026
Yes, they do. Scientifically interesting … you are exposing them to misinformation again, but might be fine be bc you also show the note.
120
Reposted by Martin Saveski
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.
23012
Reposted by Martin Saveski
Johan Ugander @jugander.bsky.social · 18/08/2026
New work out in PNAS studying what values were amplified on X (in Oct 2024), led by @ziv-e.bsky.social, paper here: www.pnas.org/doi/10.1073/... coverage below!
pnas.org
Value misalignments in X’s feed algorithm is a reflection of value tensions in engagement | PNAS
Social media feed algorithms rank content that is purported to be preferred by users, but the engagement behaviors that drive these algorithms are ...
1268
Reposted by Martin Saveski
Maria Antoniak @mariaa.bsky.social · 12/08/2026
Check it out! Lea is live and open to the public 🥳 Lea is an experiment to build better social media by researchers and for researchers, where we own our own data and can build our own feeds, events, and communities. This is still very much a proof-of-concept; we welcome ideas + collaborators!
2024285
Martin Saveski @msaveski.bsky.social · 27/07/2026
We will cover: - History and foundations of feed algorithms - Key ideas behind running experiments using middleware - Hands-on exercises on designing feed experiments using browser extensions or on Bluesky.
050
Martin Saveski @msaveski.bsky.social · 27/07/2026
Looking forward to giving a tutorial on 𝗦𝗼𝗰𝗶𝗮𝗹 𝗠𝗲𝗱𝗶𝗮 𝗙𝗲𝗲𝗱 𝗥𝗮𝗻𝗸𝗶𝗻𝗴 𝗔𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺𝘀 with @tiziano.bsky.social at @ic2s2.bsky.social! 🕜 𝗧𝗶𝗺𝗲: Tuesday, 1-4 pm 📍 𝗟𝗼𝗰𝗮𝘁𝗶𝗼𝗻: Mansfield (210). 🌐 𝗪𝗲𝗯𝘀𝗶𝘁𝗲: social-media-ais.github.io/ic2s2-26-tut...
1307
Martin Saveski @msaveski.bsky.social · 23/07/2026
Congrats on submitting and good luck!
040
Martin Saveski @msaveski.bsky.social · 18/06/2026
Congratulation, Nathan!
131
Martin Saveski @msaveski.bsky.social · 11/06/2026
Yes!
130
Martin Saveski @msaveski.bsky.social · 11/06/2026
I am delighted to hear! Hopefully it replicates many times!
010
Martin Saveski @msaveski.bsky.social · 27/05/2026
Tell me how it goes! :)
120
Martin Saveski @msaveski.bsky.social · 27/05/2026
Not AI but big white spot, dark, and round is my heuristic.
110
Martin Saveski @msaveski.bsky.social · 16/04/2026
Congratulations, Robb!
110
Reposted by Martin Saveski
Brooke Foucault Welles @foucaultwelles.bsky.social · 25/02/2026
The IC2S2 deadline is right around the corner! We really need more reviewers to make this conference work. I know (I KNOW) you all get a lot of requests but please consider signing up, especially if you submit. It’s just a few abstracts, we’ll keep the review load light. Promise!
074
Reposted by Martin Saveski
Dean Eckles @eckles.bsky.social · 18/02/2026
⚙️ Working at the intersection of causality and networks? We're organizing a satellite event at @netsciconf.bsky.social in Boston on June 1st. The focus is networks science and causal inference. Submit your work by March 10th! causnets.github.io
causnets.github.io
CausNetS: Toward a Causal Network Science
A NetSci 2026 Satellite
15121
Reposted by Martin Saveski
travis lloyd (træve) @travislloydphd.bsky.social · 09/02/2026
"Community Notes" are reshaping how millions encounter information on social media--but what makes them work (or not)? We term these "Crowdsourced Context Systems" (CCS) and introduce a framework for designing and evaluating them in a new #CHI26 paper 🧵
2296
Martin Saveski @msaveski.bsky.social · 23/01/2026
Consider submitting an ICWSM workshop proposal! It’s a great opportunity to create space for discussions around emerging research threads, new methods, or even old but exciting topics. Deadline: Jan 30.
162
Martin Saveski @msaveski.bsky.social · 11/12/2025
I feel like colleagues are winking at me when they write a descent letter but don't select the highest option 😀
010
Martin Saveski @msaveski.bsky.social · 11/12/2025
I didn't expect this until I was on the other side, but I do find them a bit informative. The culture is such that ppl feels they need to write a "good" letter and you can emphasize the positive aspects in the letter. But when explicitly asked, I think most people find it hard to be untruthful.
100
Reposted by Martin Saveski
Manoel Horta Ribeiro @manoelhortaribeiro.bsky.social · 09/12/2025
The Center for Information Technology Policy at Princeton invites applications for a Postdoctoral Fellow to work with Andy Guess (Politics/SPIA), Brandon Stewart (Sociology), and me (CS). puwebp.princeton.edu/AcadHire/app... Please apply before Sunday, the 13th of December!
01610
Reposted by Martin Saveski
Jay Van Bavel, PhD @jayvanbavel.bsky.social · 09/12/2025
Some social media algorithms are feeding us antidemocratic attitudes and intergroup hostility. But a new field experiment finds that an algorithmic feed can reduce out-group animosity & affective polarization by down-ranking this hostile political content. www.science.org/doi/10.1126/...
0216
Martin Saveski @msaveski.bsky.social · 08/12/2025
Sure, the "dosage" of the decreased exposure intervention depends on how much AAPA participants had in their feed (per party breakdown in Fig. S3); increased exposure was similar for everyone. But reweighting by party, education, and race doesn’t change the point estimates much (see Sec. S10).
000
Reposted by Martin Saveski
University of Washington Information School @ischool.uw.edu · 04/12/2025
What if you could see fewer hostile political posts on social media? A new paper out in Science by Martin Saveski @msaveski.bsky.social of the iSchool, along with @tiziano.bsky.social, @jiachenyan.bsky.social, Jeff Hancock, Jeanne Tsai and @mbernst.bsky.social, explores this: doi.org/10.1126/scie...
Screenshot of research article in Science titled "Reranking partisan animosity in algorithmic social media feeds alters affective polarization." Full text available at https://www.science.org/doi/10.1126/science.adu5584.
1175
Martin Saveski @msaveski.bsky.social · 03/12/2025
Nice! I'm glad you enjoyed it! Actually, @jugander.bsky.social strongly recommended it to me when I was there a few years ago.
020
Martin Saveski @msaveski.bsky.social · 02/12/2025
Re SUTVA: My experience doing empirical and methodological work on interference (e.g., doi.org/10.1145/3097...) has kept me humble when trying to predict total treatment effects.
000
Martin Saveski @msaveski.bsky.social · 02/12/2025
(Also, that's where we got the idea to contextualize with historical change.)
100
Martin Saveski @msaveski.bsky.social · 02/12/2025
We actually did a thorough lit review when doing the power analysis and, if you look closely, there aren’t many experiments that used the same outcome to compare with. My best reference point is the excellent paper by Santoro & @dbroockman.bsky.social : doi.org/10.1126/scia...
doi.org
The promise and pitfalls of cross-partisan conversations for reducing affective polarization: Evidence from randomized experiments
Cross-partisan conversations can reduce affective polarization, but effects do not persist long-term or spill over.
110
Martin Saveski @msaveski.bsky.social · 02/12/2025
That’s why we tried to contextualize the results in terms of historical change in the metric.
110
Martin Saveski @msaveski.bsky.social · 02/12/2025
Well, they ask whether a 2-degree change is a small effect, and I think it’s a reasonable question. I’ve discussed this with quite a few people who have done extensive empirical work in this area and whose opinions I value. For some, 2 degrees is small; for others, it’s huge ...
110
Martin Saveski @msaveski.bsky.social · 02/12/2025
Thank you! I have been meaning to send all of your a note for while, but I can't overstate how helpful your Green Lab SOP was in analyzing the data!
110
Martin Saveski @msaveski.bsky.social · 01/12/2025
Thanks for the shoutout! Obviously many possible reasons for the differences but my best guess is (i) content vs. user level intervention (i.e., reranking content likely to polarize) and (ii) much higher prevalence of political content on X (32% on X vs. 13.4% on FB). Curious to hear your thoughts.
030
Martin Saveski @msaveski.bsky.social · 01/12/2025
Finally, in this work, we focused on affective polarization, but our framework for LLM-based feed ranking is general and can be applied to other outcomes, including well-being, mental health, and civic engagement. /fin
160
Martin Saveski @msaveski.bsky.social · 01/12/2025
We hope that other researchers will use our methodology to run experiments that are longer, span multiple platforms, and extend beyond the US. /13
110
Martin Saveski @msaveski.bsky.social · 01/12/2025
Important limitations to keep in mind: (i) this was a 10-day experiment, (ii) run on a single platform, and (iii) during a politically charged time. /12
110
Martin Saveski @msaveski.bsky.social · 01/12/2025
Increasing exposure to AAPA didn’t lead to any detectable effects on engagement, likely because we reranked far fewer posts. /11
100
Martin Saveski @msaveski.bsky.social · 01/12/2025
Reducing exposure to AAPA led to a decrease in engagement in absolute terms: less time spent, less posts viewed, and liked. However, among the posts that the participants viewed, they liked them at a significantly higher rate. /10
150
Martin Saveski @msaveski.bsky.social · 01/12/2025
Decreasing exposure to AAPA made participants less angry and sad in the moment while increasing exposure had the opposite effect. The reranking didn’t have any effect on calm and excitement. /9
Effects of reducing and increasing exposure to AAPA content in participants’ feeds on their experiences of emotion compared with that of the corresponding control group.
(Left) Participants were surveyed within the feed during the intervention [scale ranged from 0 (“none at all”) to 100 (“extremely”)] and (right) off-platform after the experiment [scale ranged from 1 (“never”) to 5 (“all the time”)]. The filled circles represent statistical significance (Padj < 0.05, adjusted for multiple hypothesis testing), and the error bars represent 95% CIs.
150
Martin Saveski @msaveski.bsky.social · 01/12/2025
While the effects are symmetric, it’s worth noting that we upranked a few APAA posts and downranked all AAPA posts in the corresponding conditions. /8
Average fraction of AAPA posts seen by participants for each day of the experiment.
140
Martin Saveski @msaveski.bsky.social · 01/12/2025
In a field experiment with 1,256 consenting participants, we found that downranking AAPA posts leads to a decrease and upranking to an increase in affective polarization of 2 degrees on the 0-100 out-party feeling thermometer. /7
Effects of reducing and increasing exposure to AAPA content in participants’ feeds on their feeling toward the out-party relative to the corresponding control group.
(Left) Participants were surveyed within the feed during the intervention and (right) off-platform after the experiment. The feeling thermometer scale was between 0 (cold) and 100 (warm). The error bars represent 95% CIs.
140
Martin Saveski @msaveski.bsky.social · 01/12/2025
There are many reasonable ways to define “polarizing content.” We focused on antidemocratic attitudes and partisan animosity (AAPA), drawing on the eight factors defined in the excellent study by Voelkel et al. doi.org/10.1126/scie... /6
140
Martin Saveski @msaveski.bsky.social · 01/12/2025
In contrast to previous work that intervened at the level of users (e.g., downranking in-party content) or platform affordances (e.g., switching to a chronological feed), we intervened at the content level, exploiting recent advances in NLP. /5
160
Martin Saveski @msaveski.bsky.social · 01/12/2025
We used this method to test how reranking content that is likely to polarize affects participants’ affective polarization and emotions. /4
140
Martin Saveski @msaveski.bsky.social · 01/12/2025
The extension intercepts the user’s feed, uses an LLM to score and rerank the posts, and displays the updated feed. Making this process fast took a lot of @tiziano.bsky.social’s engineering wizardry. Source Code: github.com/StanfordHCI/... Technical report: arxiv.org/abs/2406.19571 /3
140
Martin Saveski @msaveski.bsky.social · 01/12/2025
Feed algorithms impact our lives, but until now only the platforms could run experiments testing the causal effects of different design choices. We propose a possible solution to this challenge by deploying a field experiment on X using a browser extension. /2
140
Martin Saveski @msaveski.bsky.social · 01/12/2025
Joint work with @tiziano.bsky.social, @jiachenyan.bsky.social, Jeff Hancock, Jeanne Tsai, @mbernst.bsky.social Link: doi.org/10.1126/scie... And a very thoughtful perspective by @jennyallen.bsky.social and @jatucker.bsky.social: doi.org/10.1126/scie... /1
242
Martin Saveski @msaveski.bsky.social · 01/12/2025
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. 🧵
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.
515468
Martin Saveski @msaveski.bsky.social · 30/11/2025
The Louisiana museum is really nice. Short train ride but worth it.
120
Reposted by Martin Saveski
Johan Ugander @jugander.bsky.social · 18/11/2025
📣 Postdocs at Yale FDS! 📣 Tremendous freedom to work on data science problems with faculty across campus, multi-year, great salary. Deadline 12/15. Spread the word! Application: academicjobsonline.org/ajo/jobs/31114 More about Yale FDS: fds.yale.edu
academicjobsonline.org
Yale University, Institute for the Foundations of Data Science
Job #AJO31114, Postdoc in Foundations of Data Science, Institute for the Foundations of Data Science, Yale University, New Haven, Connecticut, US
02413
Reposted by Martin Saveski
Soham De @sohamde.in · 07/11/2025
🚨 New paper! 🔍 “Question the Questions: Auditing Representation in Online Deliberative Processes” In deliberative polls, participants propose questions for experts but only a few make it to the panel. How representative are those chosen questions of everyone’s interests? 🧵👇
182