If there are any public datasets on trolling, please point me to it. It should not be that difficult to build reliable tools. The biggest challenge would be to get both the response & the trolling so that these pairs will provide statistical / ml clues to identify trolling.
And same software that can filter out trolls online. Sadly #nlp is not yet reliable to do this accuratelyhttps://twitter.com/jenheemstra/status/1076103230109745153 …
-
-
-
Arguably impossible - language allows for too many entendres.
#nlp filters can maybe raise the level of the misogyny and trolling but their use would at best be a suboptimal solution. - Show replies
New conversation -
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.