Johan Ugander
LightNews LightNews
banner
jugander.bsky.social
Johan Ugander
@jugander.bsky.social
3.3K followers 510 following 150 posts
Associate Professor, Yale Statistics & Data Science. Social networks, social and behavioral data, causal inference, mountains. https://jugander.github.io/
Posts Replies Media Videos
Pinned
jugander.bsky.social
Johan Ugander @jugander.bsky.social · Jul 1
📣 Update: I've moved to Yale, joining the Department of Statistics & Data Science as an Associate Professor today (July 1)! The last year's sabbatical here has been great for me and my family, and I am excited for great things ahead! Come visit! Trading the wind of freedom for light and truth!
Yale shield
Reposted by Johan Ugander
kashhill.bsky.social
Wall Street Journal got an A.I.-run vending machine for their office.

Takeaway: Highly entertaining, but financially disastrous to let a generative A.I. chatbot run your business. www.wsj.com/tech/ai/anth...
We Let AI Run Our Office Vending Machine. It Lost Hundreds of Dollars.
An AI agent ran a snack operation in the WSJ newsroom. It gave away a free PlayStation, ordered a live fish—and taught us lessons about the future of AI.
www.wsj.com
December 18, 2025 at 5:24 PM
Reposted by Johan Ugander
adam-lg.bsky.social
"Low-rank Covariate Balancing Estimators under Interference"
Always neat to see CBPS in the wild

arxiv: arxiv.org/abs/2512.13944
#statssky #causalsky
A key methodological challenge in observational studies with interference between units is twofold: (1) each unit's outcome may depend on many others' treatments, and (2) treatment assignments may exhibit complex dependencies across units. We develop a general statistical framework for constructing robust causal effect estimators to address these challenges. We first show that, without restricting the patterns of interference, the standard inverse probability weighting (IPW) estimator is the only uniformly unbiased estimator when the propensity score is known. In contrast, no estimator has such a property if the propensity score is unknown. We then introduce a \emph{low-rank structure} of potential outcomes as a broad class of structural assumptions about interference. This framework encompasses common assumptions such as anonymous, nearest-neighbor, and additive interference, while flexibly allowing for more complex study-specific interference assumptions. Under this low-rank assumption, we show how to construct an unbiased weighting estimator for a large class of causal estimands. The proposed weighting estimator does not require knowledge of true propensity scores and is therefore robust to unknown treatment assignment dependencies that often exist in observational studies. If the true propensity score is known, we can obtain an unbiased estimator that is more efficient than the IPW estimator by leveraging a low-rank structure. We establish the finite sample and asymptotic properties of the proposed weighting estimator, develop a data-driven procedure to select among candidate low-rank structures, and validate our approach through simulation and empirical studies.
December 18, 2025 at 2:57 AM
Reposted by Johan Ugander
dmimno.bsky.social
Use AI unto others as you would have them use AI unto you
December 16, 2025 at 5:54 PM
jugander.bsky.social
There's an old social media post, lost to time, that goes something like: if you really want to be successful, make sure you wake up every morning and select on the dependent variable. (Guidance counselors hate this one weird trick!) poetsandquantsforundergrads.com/news/which-u...
Which Undergraduate B-Schools Are Most Likely To Produce A Unicorn Founder? This Stanford Prof Has Answers
Dream of building a unicorn? New Stanford research reveals which undergraduate schools most increase the odds.
poetsandquantsforundergrads.com
December 16, 2025 at 2:03 PM
Reposted by Johan Ugander
jakehofman.bsky.social
We're hiring interns in the Computational Social Science group at Microsoft Research NYC!

If you're interested in designing AI‑based systems and understanding their impact at both individual and societal scales, apply here by Jan 9, 2026: apply.careers.microsoft.com/careers/job/...
Research Intern - Computational Social Science | Microsoft Careers
Research Interns put inquiry and theory into practice. Alongside fellow doctoral candidates and some of the world's best researchers, Research Interns learn, collaborate, and network for life. Researc...
apply.careers.microsoft.com
December 15, 2025 at 4:33 PM
Reposted by Johan Ugander
princeton.edu
A new app developed at @princetoncitp.bsky.social allows researchers to construct a large-scale dataset that aggregates individual worker data across many thousands of rides to shed light on the working conditions of rideshare drivers.
Princeton Engineering - New tool drives gig workers toward wage transparency
A new tool developed by Princeton researchers provides gig workers access to aggregate wage data that companies do not provide, a boon for rideshare labor
bit.ly
December 10, 2025 at 8:30 PM
Reposted by Johan Ugander
andyguess.com
The Center for Information Technology Policy at Princeton invites applications for a Postdoctoral Fellow to work with an interdisciplinary team (me, @bstewart.bsky.social, and @manoelhortaribeiro.bsky.social).

Link: puwebp.princeton.edu/AcadHire/app...

Please apply by THIS SUNDAY, Dec. 14!
We are seeking a Fellow to lead cutting-edge research on short-form video content and its societal implications. Bridging the gap between computer vision, causal inference, and computational social science, the Fellow will focus on the large-scale analysis of TikTok data (using an existing, massive dataset). The position involves developing novel multimodal methods to understand how short-form algorithmic content shapes public opinion, political polarization, and online culture. This is a unique opportunity to work at the forefront of the field, combining rigorous social science research designs with state-of-the-art computational techniques.
December 9, 2025 at 9:34 PM
Reposted by Johan Ugander
msaveski.bsky.social
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.
December 1, 2025 at 7:59 AM
Reposted by Johan Ugander
frapierri.bsky.social
Happy to announce the 2nd edition of our Summer School in Computational Social Science that will take place in the beautiful Villa del Grumello on Lake Como between June 22-26, 2026!

*** DEADLINE FOR APPLICATION: February 15, 2026 (firm deadline) ***

More details here:
css2.lakecomoschool.org
November 27, 2025 at 5:21 PM
jugander.bsky.social
"Understanding the strengths and limitations of community-based responses to misinformation" — very nice commentary by @ekvraga.bsky.social in PNAS, covering my recent paper on causal effects of Community Notes w/ @isaacslaughter.bsky.social @axelp.bsky.social @msaveski.bsky.social
PNAS
Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...
www.pnas.org
November 26, 2025 at 7:35 PM
Reposted by Johan Ugander
cwarzel.bsky.social
I wrote about the fake account blowup on X this weekend. A genuine post-truth nightmare and proof that these companies have polluted their platforms so thoroughly and traded reality for profit that they've undermined the very idea of what the internet is supposed to be.
That MAGA Account Might Be a Troll From Pakistan
How X blew up its own platform with a new location feature
www.theatlantic.com
November 24, 2025 at 4:33 PM
jugander.bsky.social
Powerful read. If you're a US resident age 18-35, consider registering for the National Marrow Donor Program (NMDP, formerly BeTheMatch): www.nmdp.org
A Battle with My Blood
When I was diagnosed with leukemia, my first thought was that this couldn’t be happening to me, to my family.
www.newyorker.com
November 23, 2025 at 4:15 AM
Reposted by Johan Ugander
nachristakis.bsky.social
Yale’s Institute for Foundations of Data Science (FDS) @yaledatascience.bsky.social is seeking applications for postdoctoral positions. These are cool, generously supported, competitive positions, expected to last 2-3 years, for independent scholars working on the foundations of data science.
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
academicjobsonline.org
November 17, 2025 at 8:08 PM
jugander.bsky.social
📣 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
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
academicjobsonline.org
November 18, 2025 at 3:54 AM
jugander.bsky.social
New office trinket: I 3D-printed "Lewitt's missing cube". Quite happy with how it turned out. Many thanks to Paul for sending me the stl file! Skip to 49:55 in his video to appreciate why this is fun.
Lewitt's missing cube.
November 4, 2025 at 9:21 PM
jugander.bsky.social
Excellent report on experiences of @guidoimbens.bsky.social & Mary Wootters co-teaching "Causality, Decision Making, and Data Science" to undergrads at Stanford fall 2024: hdsr.mitpress.mit.edu/pub/uynpjlow... Course material here: stanford-causal-inference-class.github.io
November 3, 2025 at 4:14 PM
Reposted by Johan Ugander
alondra.bsky.social
ICYMI: Drop everything and spend 13 minutes with Amy Sherald--with her singular vision and talent, with her clarity about her central place in the jagged American story. You will be stirred by it all. www.cbsnews.com/video/amy-sh...
Artist Amy Sherald: The 60 Minutes Interview
Amy Sherald spent years painting in obscurity, and almost died from a rare heart condition. Now 52, the artist behind Michelle Obama's official portrait is one of America's most celebrated painters.
www.cbsnews.com
October 26, 2025 at 6:39 PM
jugander.bsky.social
Connecticut is approach peak fall. Shots from Lake Wintergreen this morning. A glorious start to the day.
Lake Wintergreen with fall foliage. Lake Wintergreen with fall foliage.
October 24, 2025 at 3:21 PM
Reposted by Johan Ugander
bostonjoan.bsky.social
New paper alert!!! 🚨

“A Short History of Misinformation-at-scale and Efforts to Mitigate it” in the Journal of Public Policy and Marketing

drive.google.com/file/d/1Klg9...

This article traces the social construction of misinformation-at-scale through changes to content moderation.
donovan-2025-express-a-short-history-of-misinformation-at-scale-and-efforts-to-mitigate-it.pdf
drive.google.com
October 16, 2025 at 9:04 AM
Reposted by Johan Ugander
mathewkiang.com
Have you ever wondered how to ensure a loss in Candyland though?

github.com/mkiang/candy...
github.com
October 6, 2025 at 4:40 PM
Reposted by Johan Ugander
yaledatascience.bsky.social
Join the Social Algorithms Workshop at Yale to learn how algorithms amplify ideas, and (sometimes) mislead us, organized by @jugander.bsky.social w/ talks by @brendannyhan.bsky.social & @informor.bsky.social. Use code sawitonX on last registration page for 25% off yalefds.swoogo.com/socialalgori...
October 6, 2025 at 3:21 PM
jugander.bsky.social
Re-upping for 2025.
apoorvalal.com apoorva lal @apoorvalal.com · Oct 9
The Manski bound for the number of Nobel Prizes received by Chuck Manski by next Monday is [0, 1]
October 6, 2025 at 2:45 PM
Reposted by Johan Ugander
economeager.bsky.social
"Many people still have an elderly relative who survived a bout of severe childhood illness; not one of us has an elderly relative who did not."

This is the best and perhaps most important illustration of sample selection i have seen in a good long while.
trevondlogan.bsky.social Trevon Logan @trevondlogan.bsky.social · Sep 29
Good history helps us avoid nostalgia. The great article “Economic History and the Historians” (2020) by Anne McCants reminds me why nostalgia can get us in trouble. Two of her examples are very relevant to today: vaccinations and the popular narrative of some economic “good old days.”
Getting vaccinated is unpleasant. Dying of measles is worse. In the decade before the 1963 vaccine for measles emerged, an average of 475 Americans died from measles every year, most of them children. This (absolute) number had dropped to a low of 1 in 1981, despite a steadily increasing population that might have hypothetically contributed additional cases. Sadly, the number of measles cases in the United States has been steadily climbing upward again because we seem not to remember the ravages of the disease so much as the inconvenience of the shot—even without taking into account the absurd rejection of the solid scientific evidence in favor of vaccinations. Many people still have an elderly relative who survived a bout of severe childhood illness; not one of us has an elderly relative who did not. The blurring of the historical evidence for and against vaccination that arises from strangely incongruous historical narratives allows a seemingly inconsequential but nonetheless deadly nostalgia to run rampant. Another example of dangerous reverence for the past concerns the flurry of popular enthusiasm lately (at least if the pundits of the 2016 American election are to be believed) for the “good old days” of the 1950s when a family could live securely on just one income (in these nostalgic accounts, that one income is usually a man’s). Lest we forget, these are the same good old days of poor air quality and measles. Maybe trivial in comparison but certainly indicative of the scope of the cognitive problem that nostalgia presents, the average size of a new home built in America in 1950 was 983 sq. ft.; by 2010, the average size had risen to 2,392 sq. ft. Given that families were larger on average in the 1950s than they were in 2010, per capita space allocation had risen even faster than total area. Although we might not need that much personal space, many of us have become used to it. Older furniture now looks tiny compared to what is now on offer in showrooms, whereas older television sets were behemoths with miniscule screens showing programs in glorious black and white.
October 1, 2025 at 10:45 AM
Reposted by Johan Ugander
pessimistsarc.bsky.social
Happy Birthday Google

For many of your 27 years you were called a lazy vice. Finally you have attained the status of a thoughtful virtue of the good old days.

🥂 🥳
September 27, 2025 at 10:30 PM