[SkyMarshal]

I wonder if people make distinct enough facial expressions while reading online content for this to work. For myself, I pretty much stare blankly at the screen the whole time without much change in my expression. The ML would have to be very good at detecting slight nuance.

[hairofadog]

To your point, one of the things I worry about with apple news, for example, is that the underlying ai won’t understand _why_ I dislike a particular news story. Generally I downvote hyperbole, clickbait, and paparazzi content, but I would guess it’s more common for people to downvote things based on the substance of a story, e.g. downvoting a well-written, truthful article because the truth in that case is inconvenient for their political stance, or because it’s about a loathsome-yet-newsworthy person. A facial recognition system would have to know the difference between my face being frustrated at a high-quality story about the fires in the western states vs my frustration that apple news seems to find Andy Borowitz to be hilarious and relevant. Maybe possible, but lots of nuance under the surface.

[AndrewThrowaway]

While your face might seem still, e.g. your heartbeat, your eye movements can reveal a lot.

I remember how I was blown away by this video a few years ago:

https://youtu.be/3rWycBEHn3s?t=171

[thrav]

Wasn’t there a proof of concept for exactly this about how social media apps were probably already doing this? I believe I saw it on HackerNews. It was a site where you gave them camera access and then ran something like a 60 second experiment. Seemed academic.

[almyndz]

yeah, usually when I'm reading the news I'm only screaming on the inside