These young people are, in their own way, teaching seminars on identity every time they post. And it reminds me that the best social science takes what folks already sense about the world and treats it with the theoretical and empirical seriousness it deserves.

www.instagram.com/reel/DQ-1vvq...

This project has been years in the making — and it’s been an absolute joy working with @avamadesousa.bsky.social, Lauryn Hoard, Wendi Gardner, @williambrady.bsky.social, and @sylviapperry.bsky.social.

So grateful for this team. 🙏
Full preprint here: osf.io/preprints/ps...

Across both studies, justification consistently aligned with less support for police reform, while outrage aligned with more.

That link between outrage and reform was strongest for the Black victim — raising questions about how racialized stereotypes might blunt the very outrage needed for change.

Study 2: Participants watched two matched videos—one with a Black victim, one White.

Those who endorsed more justification also reported less outrage and lower support for reform.
When the victim was Black, participants more often described him as “superhuman.”

Comments justifying police conduct were ~80× less likely to mention accountability.
Outrage comments were ~11× more likely.

In public conversation, justification and outrage emerge as opposing ways of interpreting the same harm.

Study 1: We analyzed 250k YouTube comments from 57 videos of police brutality using GPT-3.5 + Google Jigsaw.

Two main reactions appeared:
➡️ Justifying the officer’s actions
➡️ Expressing moral outrage

They rarely overlap — each offers a different lens. ⚖️

Thank you so much Abby ❤️🥹

Thank you so much family! Hope you’re doing well!!

🎓 Paper: osf.io/preprints/os...
📺 YouTube Tutorials: youtube.com/playlist?lis...
📦 GitHub: github.com/jedoriscar/U...

#RStats #MachineLearning #SocialPsych #AcademicTwitter #DataScience

This paper was a labor of love and I’m so grateful to my brilliant co-authors Michalis Mamakos, @sylviapperry.bsky.social , and Tessa Charlesworth for their support, feedback, and generosity throughout the process.

We also include extensive annotated R code, visual walkthroughs, and a free YouTube tutorial series to make this genuinely hands-on. If you’re curious about how UML can help you uncover new patterns in your data—or just want to brush up on clustering and dimension reduction—check it out!

Each section walks through:

- what the method is

- how to implement it in R

- how to interpret the results

- real examples using Project Implicit data

We focus on 4 key UML techniques:

- K-means clustering

- DBSCAN

- Principal Component Analysis (PCA)

- Market Basket Analysis (MBA)

Social cognition research is drowning in big, complex data—but we often use the same familiar methods. Unsupervised Machine Learning (UML) gives us tools to explore patterns without predefined outcomes. We wrote this paper to demystify UML and help researchers use it meaningfully.

🧵 A brief thread on what this tutorial paper is about & why I’m excited about it:

Let’s gooooo! Dr. Vallabha has a nice ring to it!

I would like to share that the family requests donations be made to the Innocence Project (innocenceproject.org/donate/) or the American Civil Liberties Union (action.aclu.org/give/now) in lieu of flowers. 💖💐