Our article "Norm-enhanced prebunking for actively open-minded thinking indirectly improves misinformation discernment and reduces conspiracy beliefs" has now been published open access in JESP!
@rakoenmaertens.bsky.social
@profsanderlinden.bsky.social
authors.elsevier.com/sd/article/S00…
🧵👇

9/
Finally—cosine is not the only similarity metric out there. We go through the pros and cons of each, with advice about when e.g. dot product is more effective.

8/
You may think good and evil are opposites, but your embedding model might think: “Those are both moral judgements! Very similar!” If your construct has an opposite, consider using an anchored vector.

7/
CAV = learn a vector representation from labeled examples. Humans rate a few posts; you apply the pattern to analyze new texts! This new method gives precise, interpretable scores if you have relevant training data on hand.

6/
CCR = embed a questionnaire. Very powerful when your texts are similar to questionnaire scale items (e.g. open-ended responses). We point out a risk—if you aren’t careful, you might measure how much your texts sound like psychological questionnaires—but there are solutions!

5/
DDR = average embedding of a word list. Great for summarizing abstract dimensions (emotion, morality) across genres. Not good for more complex constructs. NEW important tip: weight words by frequency to reduce noise from rare words.

4/
We review 3 ways to improve on traditional methods: Distributed Dictionary Representation (DDR), Contextualized Construct Representation (CCR) & our new Correlational Anchored Vectors (CAV).
Each has advantages and disadvantages.

3/
Your trusty Likert scale questionnaire could be free response instead.
Your validated word list could be leveraged to analyze words that aren’t included.
Your painstaking MTurk-rated dataset could be extended to analyze 10,000 social media posts.

2/
What’s an embedding?
Why choose one model over another?
Why do you need embeddings when you can ask ChatGPT to rate your texts?
Take a look: doi.org/10.31234/osf...

New conceptual review + tutorial on text embeddings out in #APA_Journals w/ @almogsi. Beginner-friendly, but experts will find spicy new takes as well. Tag a colleague who’s still counting words... #RStats #tidyverse #quanteda
1/

Word embeddings are still the right tool for studying words.

I talked about ideology, curation bubbles, (mis)information, and, of course, transaction costs with Mike Munger on The Answer Is Transaction Costs: taitc.buzzsprout.com/2186249/epis...

(1/9) Excited to share my recent work on "Alignment reduces LM's conceptual diversity" with @tomerullman.bsky.social and @jennhu.bsky.social, to appear at #NAACL2025! 🐟

We want models that match our values...but could this hurt their diversity of thought?
Preprint: arxiv.org/abs/2411.04427

How politicians communicate shapes online discourse in ways we might overlook.

Our new paper shows that their choice between a fact-based (evidence-driven) and a belief-based (sincerity-driven) honesty creates a "contagion" effect, influencing how users engage and respond. ⬇️(1/8)

This week I finished teaching my mixed models #stats course @ BGU university!

You can find all the updated #rstats and #lme4 related materials here:

github.com/mattansb/Hierarchical-Linear-Models-foR-Psychologists

Extremely happy to share that "Curation Bubbles" is online (open access!) at @apsrjournal.bsky.social: www.cambridge.org/core/journal...

Our paper is finally out!

🔊 New paper just accepted in JPSP 🥳

In "Inference from social evaluation", we explore how people use social evaluations, such as judgments of blame or praise, to figure out what happened.

📜 osf.io/preprints/ps...

📎 github.com/cicl-stanfor...

1/6