limone.eth 🍋
@limone.eth
👀 Introducing Findcaster: a tool to discover people around web3 socials Search people by topics they are interested in and POAPs they collected around the world ✨ https://findcaster-kappa.vercel.app https://x.com/limone_eth/status/1695119625300619421?s=46&t=mKiZ-uJIBkxN1Abfee_G4g
5 replies
5 recasts
19 reactions
Gabriel Ayuso
@gabrielayuso.eth
This is cool! For keyword based search, it'd be great to show examples of casts where the keyword was used. An interesting more advance feature would be some form of sentiment analysis. Are they positive or negative about the keyword. "NFTs are stupid" is very different to "I minted this NFT"
3 replies
0 recast
1 reaction
blobs
@blobs
👋 im working on this with https://github.com/michaelhly/FarGlot we’ll tune a pretrained BERT model based on the farcaster corpus and expose a sentiment analyzer based on the tuned model should have something out next week!
2 replies
0 recast
1 reaction
blobs
@blobs
… but well probably need to have a django server to be able to use this in product 😕 @limone.eth let me know if you want to collab
2 replies
0 recast
1 reaction
blobs
@blobs
or maybe we can stick the analyzer in https://operator.io’s langchain flow!
0 reply
0 recast
0 reaction
