91–100 of 101 posts
I continually see the same bunch of shows when browsing that I will never, ever watch. They take up space and add to cognitive load and ultimately just annoy me each time I see them in the list.
I'm sure this weighting would also be very useful from an algorithmic recommendations view as well.
Its a bit the same as dating algorithms. If the algorithm was to good there would be no paying users of the service.
My major problem with almost all recommendation engines and add-ons is that most of the time I want a recommendation that is orthogonal to the last thing I watched.
If I just watched a Japanese yakuza crime thriller I don't want you to recommend another Japanese yakuza crime thriller. Give me something as good as what I just watched but different. But that's me. Many people just want to watch Hallmark Christmas romances until their heads explode.
That's probably why I still use Criticker. Because it gives you one choice across multiple genres.
Maybe recommendations are harder than we think because our tastes are too arbitrary and unpredictable. Maybe overlapping with someone else's tastes actually predicts nothing about whether there are any more places we will overlap, so it's not the simple data processing problem that we wish it to be. I've tried all sorts of "people who liked X also enjoyed Y" book and movie lists and it never seems any better than a g…
When I meet people with seemingly the same taste, usually we exchange our trophies, eg my latest
This is going to hurt (series) - 2022 - UK
En man som heter Ove - 2015 - Sweden
All That Breathes - 2022 - India
Jeanne Dielman, 23, quai du Commerce, 1080 Bruxelles - 1975 - BelgiumIMO, they don't use anything like that now for streaming. It's as others have said: this is what we want you to watch, not what you necessarily will like.
As someone that has worked within one of these orgs, it's because the recommendation system has been captured by contract negotiations and forced merchandising. You are not seeing things they think you would like. You are seeing the things they want you to watch.
Maybe recommendations are harder than we think because our tastes are too arbitrary and unpredictable. Maybe overlapping with someone else's tastes actually predicts nothing about whether there are any more places we will overlap, so it's not the simple data processing problem that we wish it to be. I've tried all sorts of "people who liked X also enjoyed Y" book and movie lists and it never seems any better than a g…
Belgium Canvas has several superb movies and series, every week , year-in year-out. Humans select them, not software. Selecting movies/shows is a profession and I’m positive that many people can learn it. When I meet people with seemingly the same taste, usually we exchange our trophies, eg my latest This is going to hurt (series) - 2022 - UK En man som heter Ove - 2015 - Sweden All That Breathes - 2022 - India Jeann…
The idea of a recommendation engine in these comments is generally a holy grail that can predict shows you will like personally that aren't necessarily well-rated by other people. Shows that don't simply show up in the platform's "critically acclaimed" section.
Though your post is a good example of why word of mouth recommendations are important. Netflix could have the best recommendation system in the world yet it cannot recommend any of the great shows it doesn't have to show you.
Totally agree, that's why I gave up on it myself and created an aggregator. https://tomatotree.tv
For example, The Great Pretender is at 100% from critics but doesn't show up at all here.
If you spent 20 mins looking, it's not their recommendation system that's failing. It's that you don't like their content (or how their content is portrayed). The recommendation system is the thing that shows you stuff without you needing to browse for 20 mins.
Also paradox of choice / overchoice phenomena, where the more options you have, the less you feel satisfied with any of them.
It was much easier to choose a film to watch in the cinema (about 5 options) than to choose a film from the video store (500 options).
But part of the problem the algorithm has is that content is of very uneven quality. I look at very recent things that, a few years ago, I would have wanted to see, and scroll on by. The first Avengers movie? Kind of rushed but acceptable. Thor Love and Thunder? Garbage. (Not Netflix examples, just examples)
We want to see new content but have learned from recent experience that it's not worth the trouble. The algorithm simply can't understand that.