2y ago

Where can I get the data about Lemmy subscription patterns?

I have a fair amount of experience with data visualization, analysis etc and thought it would be a fun project to try to visualize the Lemmy network, specifically which instances have strong links to one another via subscriptions from users in one to communities in the other.

How/where can I get that data?

EDIT: It sounds like many people would find this a violation of their data privacy and I simply shouldn’t do it. I had thought this kind of data was intended to be entirely accessible by design, but I learned something new!

22 comments

Likely within the API, but I would say be cautious as people on the fediverse really do not like having their data scraped, especially for projects like this.
- I think this is fine - people I've seen who objected to this kind of project were more about their account being indexed. Projects like respective size of instances were always fine
- Interesting. Isn’t it entirely public though?
  
  Yes, still doesn't make people fine with it. People defederate over stuff like that on mastodon. It's often seen as violating peoples privacy.
Probably would need to scrap this data from all the various instances to build up the dataset:
https://lemmy.ml/instances
https://lemmygrad.ml/instances
https://hexbear.net/instances
https://lemmy.world/instances
I mean the fediverse isn't exactly super mature; from what I know you should expect that you'll have to generate that data yourself some way or another.
Personally I would love to see this kind of project done. But for it to work most people on the servers data that you are working with would have to be informed and given time to answer. I hope you reach out to the administrators of each instance and ask them if they would be ok with this and give them time to ask their users. Knowledge is power and if the visualization was public I think it could be helpful.
- Thanks for the support! I thought it would be a useful tool too. People could use it to find instances they didn’t know about, but which are popular in their network, or to find under appreciated instances to build bridges.
  Anyway, sounds like database access is a must, and I’m not trying to take on a massive data wrangling exercise. I had it in my mind that the data were just sitting their for download, which was wishful thinking!
  
  If you are interested there is a professor named Damon Centola that might be interested in dedicating time to gathering that data and might help with the visualization as well. If you are in the sociologist space or just interested you could reach out to him.
  
  Sorry for commenting again but I think there is a way for you to do this in a completely open, easy, and privacy-preserving way. You don't need to access their database.
  Get a list of instances that you want to look at the subscription patterns for. (All the instances here + Lemmy.world)
  Go to that instance's website, click the "Communities" tab at the top, and then click "All" It shows how many users from that instance are subscribed to that community (both communities from that instance and outside of that instance)
  If you find a way to automatically (or manually) scrape this data from all of those websites you can create the visualization that you were talking about.
  So you were right, the data is open source it is just specific to each website.
I don't think you could do it without DB access, but not 100% sure

22 comments