You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Interesting question would then be: can you train a model to guess which one a human would prefer? And then reverse engineer what features, colors, parts of the faces, etc. are more likely to be looked at and preferred by humans?
Well, I'm guessing having all of these would give you some sort of "ranking" between different images? A model would have to guess that ranking again, with a few images taken out as validation. Class activations maps could be used to find which part of the image is used when?
Yeah I was thinking along those lines. Sounds like easier said than done though.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
