Is anyone doing movie recs based on deep learning + the individual frames in each movie? I think that could be an interesting way to learn nuanced things like "you like heist movies with mixed gender casts" or "you hate action movies that have too many gunfights."
-
I worked on a movie site at one point. The big insight was that movies aren’t like books - most ppl agree on which movies are ‘good’ vs ‘bad,’ and most ppl just want to watch ‘good’ movies.
I.e. if you liked Shawshank Redemption, doesn’t mean you want to watch B movies about being in prison. It means you want to watch other good movies, even if they are completely unrelated.
-
-
Once you start filtering based on ‘good’ movies, you realize the problem isn’t discovery - it’s that the quantity of good movies is very low.
-
Not sure I agree. I think it's a probability distribution: - 95% chance I'd like an 8 star IMDB movie - 60% for 7.5 stars - 30% for 7 stars etc. But there are so many more 7-star movies than 8.5-star ones. I want something that helps me avoid the 70% of 7-star movies I'd dislike.
- 1 more reply
New conversation -
-
-
In some ways I think it is. I’ll read good writing on most subjects. Eg reading
@michaelpollan on gardening doesn’t mean I want to read more gardening books but books written with similar style of literary prose and journalistic research.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.