Overview of the task on automatic misogyny identification at IberEval 2018

Abstract

Automatic Misogyny Identification (AMI) is a new shared task proposed for the first time at the IberEval 2018 evaluation campaign. The AMI task proposes misogyny identification, misogynistic behaviour categorization and target classification both from Spanish and English tweets. We have received a total of 32 runs for English and 24 for Spanish, submitted by 11 different teams from 5 countries. We present here the datasets, the evaluation methodology, an overview of the proposed systems and the obtained results. Finally, we draw some conclusions and discuss future work.