A claim that AI could one day deal with on-line trolls could easily be dismissed as vacuous, if it wasn’t coming from the California Institute of Technology. Current ways to detect offensive, harassing, and negative social media posts are either fully automated and not interpretable, or rely on a static set of keywords, which can ...
This story continues at AI could spot on-line trolls
Or just read more coverage at Electronics Weekly
from News – Electronics Weekly https://ift.tt/2NdG3W2
via Yuichun
沒有留言:
張貼留言