Now that Iris (npub1wnw…95l8) launched nostr-relaypool-ts, and it's working great for retrieval, I started to focus on what I originally was interested in: ranking.
So far it's in the planning stage, but I think it's going well. For now I'm planning on developing a pLike | note model (predicting whether a note is going to be liked by a user). I'm planning to use logistic regression with the following signals as a start:
- time passed since note was created
- note's author is followed by user
- number of likes
- number of comments
- share of likes from the author by the user in the past
- does it contain image?
- does it contain link?
- does it contain video?
- text length
- likes by followers
Some are easier to implement, some are a bit harder, and of course I'll check their impact before launching them.
I think I will order threads by the maximum probability that a note has in a thread. Also pLike can be used as a filter for comments to be shown / hidden. Of course pComment model can be trained on the same signal.
aritter / Adam Ritter | rbr.bio
npub1dc…ux5ey
2023-04-16 07:00:34
Author Public Key
npub1dcl4zejwr8sg9h6jzl75fy4mj6g8gpdqkfczseca6lef0d5gvzxqvux5eyPublished at
2023-04-16 07:00:34Event JSON
{
"id": "affc5691deab94b210c13cb594a1dd0089cc083df1573692e136732a5642da82",
"pubkey": "6e3f51664e19e082df5217fd4492bb96907405a0b27028671dd7f297b688608c",
"created_at": 1681628434,
"kind": 1,
"tags": [
[
"p",
"74dcec31fd3b8cfd960bc5a35ecbeeb8b9cee8eb81f6e8da4c8067553709248d",
"",
"mention"
]
],
"content": "Now that #[0] launched nostr-relaypool-ts, and it's working great for retrieval, I started to focus on what I originally was interested in: ranking.\n\nSo far it's in the planning stage, but I think it's going well. For now I'm planning on developing a pLike | note model (predicting whether a note is going to be liked by a user). I'm planning to use logistic regression with the following signals as a start:\n\n - time passed since note was created\n - note's author is followed by user \n - number of likes\n - number of comments\n - share of likes from the author by the user in the past\n - does it contain image?\n - does it contain link?\n - does it contain video?\n - text length\n - likes by followers\n\nSome are easier to implement, some are a bit harder, and of course I'll check their impact before launching them.\n\nI think I will order threads by the maximum probability that a note has in a thread. Also pLike can be used as a filter for comments to be shown / hidden. Of course pComment model can be trained on the same signal.",
"sig": "ada9a906ec9323b1487789ab3433987bcafaf603f035f84449e1f0f09f16279cb41235b0760be4317c015543687d7da257bb54ec3774cdaea69001f18abc900c"
}