Comment on First draft woes
souperk@reddthat.com 3 weeks ago
So you are basically building a classifier that tries to assert if a user will like a video. While many are against any kind of “algorithm” within the fediverse, I believe that it’s a necessity. But, I think allowing users to tag content and then building classifiers that allow you to filter based on that would be a more aligned with the fediverse.
Anyway, cosine similarity has worked for a lot of things, so I think it’s a solid foundation to get you started. Another thing you can try is using an embedding model, specifically a model that receives a segment of a video and yields a matrix with the property that similar input will result in outputs relatively close to each other (cosine or euclidean distance).
Another thing to consider is building a platform that will permanently store data. If you can come up with a set of endpoints, I can implement something in python to get ypu started. I don’t have experience with video processing so I cannot help you with that, but the crud aspect is no biggie.
Cattail@lemmy.world 3 weeks ago
I did make a classier for for videos that inputs title, tags, description, and closed caption into an LLM. I got roughly 1000 entries classified that way, issue is that most of them were non-english videos and then new videos come from somewhere on peertube that don’t hace these classifiers.
Video processing is cool just expensive computationally. Also watchers could classify the videos themselves then use a cosine similarity (or whatever algo) on that. I did suggest to peertube to share the categories people say a video is with other people (like it’s a Mastodon post) eventually it morphed into an idea light weight peertube instance that only does api.