Serious suggestion: Train a text classifier on texts from the Cultural Revolution and similar historical episodes. When you start to get matches from things written in your own time, your society is in trouble.
-
I think some of the forms of warnings are in abstract ideas that may not be in the words used or even grammar. Our society is in trouble right now. Classifier enabled.
For sure. But classifiers are surprisingly clever at detecting things. You'd be surprised. And when one does, it's credible evidence, because it's neutral.
-
-
Neutrality/normalization an interesting question here eg. what docs to train off (all or subset), ie the volume normalization between writings pro populist vs non populist, subject to a possible 51% consensus bias unless some external timeless norms set between the two sets.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I'm agreed there will be interesting information (sentiment, signals, risk, detecting more hidden objects eg 'movements') and a possible AI early warning system for societal stability, prevention of group think downward spirals ie thinking of the Communist Party of Kampuchea.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Off the back of this, detection of mind memes, viral sentences and non written viral information transfer structures (pre twitter) e.g. flags, symbols, fashion etc detecting the abstract emergent cultural structures being an interesting challenge for image/video/text classifiers.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Clever perhaps, but neutrality isnt a given.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.