How do we give recommendations when users create/post content? Like in YouTube, TikTok etc

Question

I've explored amazon personalize, etc for generating recommendations. Amazon personalize can be used when all the content is with the company/a single entity. For example, in Netflix, all the content (the catalogue of movies, tv shows etc.) is with them and they generate personalized movie/tv show recommendations.

But what if there's a platform similar to Youtube, TikTok, where users can:

- post content (users are continuously generating content)
- view other users content and interact(like, share, repost, comment)
- follow other users

When there is user generated content like this and users follow other users (meaning they probably want recommendations from users they follow), how do we give recommendations? Can we do it with Amazon Personalize? What algorithms and tools can be used?

**Lots of content - handling the cold start problem**

And when there is user generated content, there is going to be lots of content being generated every minute. So how do we handle the cold start problem (i.e. how do we decide who to recommend all of this new influx of content too)? Usually we might experiment with this new content, like recommend it to some users , see how they're responding and appropriately decide how to recommend this content. But when there is a very high frequency of content being created, how do we reduce the amount of time it takes to give recommendations/push the new content to users quickly?

And does anybody know if the questions mentioned above can be addressed using Amazon Personalize (in any way)?

Open to any and all suggestions. Thank you!

Answer

Disclaimer: I haven't still used the domain datasets as they are fairly new.

I believe you can do both parts of your questions by using the VIDEO_ON_DEMAND datasets of Amazon Personalize.

For the first part of the problem, the VIDEO_ON_DEMAND dataset gives you the option to add metadata such as the CONTENT_OWNER. [1] Even if Personalize wouldn't know who you are following, it will know you are interacting with content from a user, and that should have a similar effect.

For the second part, handling the cold start problem, you can use incremental uploads, and Personalize will retrain the model every two hours [2]. If you also use events for tracking user interactions, recommendations for new users will get relevant faster. [3]

[1] https://docs.aws.amazon.com/personalize/latest/dg/VIDEO-ON-DEMAND-datasets-and-schemas.html
[2] https://docs.aws.amazon.com/personalize/latest/dg/importing-domain-dsg-data.html#incremental-import-domain-dsg
[3] https://docs.aws.amazon.com/personalize/latest/dg/recording-events.html

How do we give recommendations when users create/post content? Like in YouTube, TikTok etc

Contenus pertinents