New machine learning models can detect hate speech and violence from texts

Myriam Douce Munezero, Phys.org, Apr 14, 2017
Commentary by Stephen Downes
files/images/emtions_in_text.PNG

This dissertation presents "a framework that can be used for the automatic detection of antisocial behavior in text. The framework is based on the emotion and language theories." I'd call this an early study as it depends on models of anti-social behaviour and then detects for them; a fuller study would develop its own models to capture a wider range of anti-social content. Still, we can see how this is useful in the context of online and learning communities. Via Helge Scherlund.

Views: 1 today, 859 total (since January 1, 2017).[Direct Link]
Creative Commons License. gRSShopper

Copyright 2015 Stephen Downes ~ Contact: stephen@downes.ca
This page generated by gRSShopper.
Last Updated: Aug 20, 2017 05:42 a.m.