Making it sustainable is the hard part. Like, I may try to patreon / kickstarter-it but... ...that's not a durable solution. But, for now, "if you build it, they will come," right?
-
-
-
like just as a graph theory problem alone. the computational resources...
0 replies 0 retweets 1 like -
What parameters would you use to categorize the “contagious” posts? Ratios?
2 replies 0 retweets 1 like -
Identities colliding in mentions; ratios; user input; a parallel social graph for sharing the negative signal. If this is your area I'd really like to talk to you about this more (right now I'm messaging between nephew easter egg hunt finds.)
1 reply 0 retweets 0 likes -
Gotcha. I’m not sure how you’d do that tbh. I don’t think ML is that refined yet wrt to user comments/negative signaling.
1 reply 0 retweets 1 like -
Replying to @CybereVitas @generativist and
You’d probably have to drastically improve current sentiment analysis algorithms. They’re just not at that point yet for the nuance required.
1 reply 0 retweets 2 likes
I have some ideas from my dissertation that I'd like to implement. I'm writing something more spec/RFC-y though. Near-term requires user inputs with examples propagated over a secondary, attenuation graph. (I added you to a notif list I have; let me know if you want off.)
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.