Thrilled to share this new paper: in a pilot randomized trial, text messages with causal information led to meaningful increases in physical activity, while non-causal texts did not. Surprisingly, people also wanted more messages than the every other day text schedule doi.org/10.2196/80090 #medsky

MIKE Chappell Roan CMAT Lady Gaga Valerie June

Thrilled to share this new paper: in a pilot randomized trial, text messages with causal information led to meaningful increases in physical activity, while non-causal texts did not. Surprisingly, people also wanted more messages than the every other day text schedule doi.org/10.2196/80090 #medsky

New paper! How many days of dietary data do we really need to collect? We find that during pregnancy it is more than many studies collect, and depends on the target being estimated (macronutrients needing most days, HEI and timing least). #nutsky doi.org/10.1016/j.aj...

New work with Dave Lagnado out now! Using qualitative + quantitative data we find people reason differently with causal information and see how they bring in prior beliefs. Call to action on methods: if we want to make claims about real world, we need to use realistic stimuli doi.org/10.3389/fcog...

I’m so excited to be speaking at this conference and looking forward to the contributed talks! What is (and should be) a variable is my absolute favorite under discussed topic in causality. Everything follows from this choice, but how should we make it?

To Be or Not to Be Included in a Causal Model February 28, 2026 @ 9:00 am - March 1, 2026 @ 5:00 pm EST Venue and Date: Center for Philosophy of Science, February 28 & March 1, 2026 Keynote Speakers: Samantha Kleinberg (Stevens Institute of Technology) Lily Hu (Yale University)

The Hidden Bias Pushing Women Out of Computing. Excited to see our paper finally being promoted! Regardless of gender, if you do applied work we find there is a real career penalty for it. But women are disproportionately affected because of diffs in research focus www.stevens.edu/news/the-hid...

I’ve written two books on causality, yet was thrilled to find a study on associations involving an understudied health condition where I think an exposure may be causal. Why? Because there was zero evidence before and without even associations it’s hard to argue it’s worth studying (and funding!).

🚨big new paper🚨Using surveys of faculty and data on >10K researchers we find 1) faculty have more negative views of applied researchers vs theoretical, 2) data shows there is a career penalty for doing applied work, and 3) women are more represented in applied research. doi.org/10.1109/ACCE... 1/5

🚨big new paper🚨Using surveys of faculty and data on >10K researchers we find 1) faculty have more negative views of applied researchers vs theoretical, 2) data shows there is a career penalty for doing applied work, and 3) women are more represented in applied research. doi.org/10.1109/ACCE... 1/5

Nice overview of our work showing responses to meals can be predicted even without microbiome and other invasive data! www.stevens.edu/news/stevens... 🩺 🖥️

If you use CGM or activity data our paper accepted to #CHIL2025 has big news: we benchmarked lots of imputation methods using real missing data mechanisms (not just random deletion) and it turns out … linear interpolation is the winner no matter what the mechanism or % missing data.

Two exciting new papers coming to CogSci 2025: Go Big or Go Hoax (the bigger the more believable for both conspiracies and facts), Causal and Counterfactual Reasoning about Gradual and Abrupt Events (timing matters for token causality and causal attribution doesn’t always track counterfactuals)

New paper just accepted to JBI: we introduce new methods for causal inference in health data with different variables for different patients. Such a common problem and yet there haven’t been any solutions!

New paper! We show incrementally retrained LSTM can be used to personalize BG forecasting for people with T1D. Best part is we can do it with a cold start! ieeexplore.ieee.org/document/107...

Thrilled to share our new paper on predicting glycemic responses to meals in people with diabetes with limited data 1) we show it can be done without microbiome or personalized training data 2) we address questions about intra individual variation! journals.sagepub.com/doi/10.1177/... 1/3 🩺 💻

“I’m alive. You’re alive. It’s beautiful. That’s why we shouldn’t be consuming life through technology.” www.nytimes.com/2025/01/30/s...

At long last! The Routledge Handbook of Causality and Causal Methods is here! I wrote a chapter on “Going from Models to Action” and the bigger question of what makes causal models useful

(For example, why is there no feedback mechanism for patients who are end recipients of clinician-focused AI tools? How can we improve the consent process for new AI tools? How can we move from fixating on AI error to addressing how to fix any errors in HC, including human errors?) bit.ly/42bkqwG

Great list and I’m thrilled to be thought of as an experimental philosopher! (Especially as I am currently writing an experimental philosophy grant proposal)

Checking out @altmetric.com’s bsky integration I was thrilled to see my collaborator Jessecae Marsh quoted in this! We didn’t study shopping but our findings did change how I approach it. There is no “best” umbrella/moisturizer/dog treat! (1/2) www.businessinsider.com/online-shopp...

Just another example of why we have to get away from the idea that more info can’t hurt, and at worst is neutral. We can’t always foresee all the risks and need to be more thoughtful about whether benefits are worth potentially unknown future harms.

Nice overview of our study showing limits of current methods to capture diet and the reality of what people eat during pregnancy www.stevens.edu/news/pregnan...

Between the NYT story on AI clones dating eachother and now AI confessionals (techcrunch.com/2024/11/18/h...) do people really want a future where AI sins and confesses for us while we stay home watching TV? I don’t need embodied clones clubbing for me, I need them to do chores so I can go out.

Amazing feeling seeing our study on diet during pregnancy finally published. We find diet varies a LOT day to day during pregnancy, eating late is linked to higher calorie intake, and more people than known are not meeting guidelines for nutrients. authors.elsevier.com/a/1k5vb54l%7...

Restarting posting over here with my recent oped @statnews.bsky.social, arguing that to get patients to share important information with them, doctors need to focus on empathy and resist the impulse to judge. www.statnews.com/2024/11/01/d...

"We were told [tracking our health] data would put us in control, but we’re actually less healthy than ever." – Dr. Samantha Kleinberg (Stevens Institute of Technology) This has me wondering how I overrate my fitness or health data. I've found it better than nothing, but some seem to disagree.

My first op-ed, out today in STAT: why your health/fitness tracker is probably measuring the wrong thing and how to have a healthier relationship with your health data www.statnews.com/2024/01/08/f...

Really enjoying preparing for my talk tomorrow. Causes are so important we need to lure people in with causal language even when not warranted... or maybe we don't need them and they're too hard to find anyway!

The talk recordings from the "Causality in Minds and Machines" workshop are live now. sites.google.com/view/causali... Thanks again to all the speakers and to the Society for Mathematical Psychology for sponsoring the workshop!