I built this because I wanted to know what I actually stop to look at when I scroll. Not what I think I look at, but what actually catches my attention. Turns out those are pretty different things.
The idea is simple: record yourself scrolling for 30-60 seconds, upload it here, and the tool figures out which posts you paused on. Then it scores each one on things like how polished the content is, how emotionally intense, whether it's the kind of stuff that makes you feel like you're missing out on something. Under the hood, it's using real computational methods from cognitive science and psychophysics—Bayesian inference, signal detection theory, the same math researchers use to study attention and perception. But you don't need to care about any of that to use it.
How to record: On iPhone, swipe down from the top-right corner and tap the screen record button (or add it in Settings → Control Center). On Android, swipe down twice and tap Screen Record. Open Instagram, scroll naturally for 30-60 seconds, stop recording, and upload the video here.
I don't know if this means anything profound. But I do think there's something interesting about seeing your attention patterns laid out like that. It felt different than I expected.
Finding the pauses. The tool watches your screen recording frame by frame. When the scroll stops for more than half a second, that's a pause—you stopped to look at something. It captures that post.
Scoring the content. Each captured post gets scored on five things: appearance focus (beauty, fashion, body stuff), how polished it looks, emotional intensity, negativity, and aspirational content (luxury, travel, success—the stuff that can make you feel like you're behind).
The final number. Your distortion score combines all of this using a version of the peak-end rule from psychology—the idea that we remember experiences by their most intense moment and how they ended. Higher score means your feed is more weighted toward engagement-bait.
A series of personal events drew my attention to the mind. After taking a class on modeling human behavior, I threw myself into computational neuroscience and started reading everything I could get my hands on.
The field can sound boring until you remember what it actually gets used for. In its more nefarious form, it crafts the algorithms and systems that exploit every manner of our mind as efficiently as possible. This is what's called the race to the brainstem—the hunt for the most effective way to hijack our most basic instincts.
I intend to be on the other side of that race. Building toward a society where technology helps us instead of preying on us. This tool is a small piece of that: making visible what usually stays hidden.
This is a toy, not science. All the thresholds are rough guesses. The scoring dimensions come from psychology research on social media effects, but I'm not claiming this is rigorous. I built it because I was curious, and I thought other people might be too.
I could be wrong about what any of this means. But I do think it's worth thinking about what we consume without choosing to—what catches our eye before we even decide if we want to see it. That felt worth exploring.
If you have thoughts about this, I'd actually love to hear them. What surprised you about your results? What didn't? Reach out at Beaum045@umn.edu—I respond to everything.
I'll send you a quick summary so you can decide if it's worth your time. No spam.