The coverage of the Netflix ratings format switch has always been frustrating to me because what people are complaining about (you're not the only one; https://www.polygon.com/2017/4/7/15212718/netflix-rating-sys...) was predictable from the beginning.
I do research in this area and it's fairly well established that when you go from something like five points to two points with ratings, you throw away tons of information. There's diminishing returns with numbers of points, but as you go lower you lose information.
The "ratings don't matter because what you want is implicit signals from peoples' actual behavior" is also disingenous because the rating behavior is a behavior that's directly tied to the stimulus in question. Not saying that indirect behavioral correlates aren't useful, only that the rating is a very powerful, direct correlate that tends to be very specific. Going back to the topic of the thread, sure, all those Facebook likes are going to be useful in predicting how much you like a candidate, but you're sure as hell going to get a lot of information by just asking them "on a scale of 1 to 5, how much do you approve of X?"
I mean it is pretty obvious that the loss of information is going to make it harder to predict. My big problem is that the system suggests completely off base content. Not to mention overly pushing their own content.
I do research in this area and it's fairly well established that when you go from something like five points to two points with ratings, you throw away tons of information. There's diminishing returns with numbers of points, but as you go lower you lose information.
The "ratings don't matter because what you want is implicit signals from peoples' actual behavior" is also disingenous because the rating behavior is a behavior that's directly tied to the stimulus in question. Not saying that indirect behavioral correlates aren't useful, only that the rating is a very powerful, direct correlate that tends to be very specific. Going back to the topic of the thread, sure, all those Facebook likes are going to be useful in predicting how much you like a candidate, but you're sure as hell going to get a lot of information by just asking them "on a scale of 1 to 5, how much do you approve of X?"