UniBO @ AMI: A Multi-Class Approach to Misogyny and Aggressiveness Identification on Twitter Posts Using AlBERTo

We describe our participation in the EVALITA 2020 (Basile et al., 2020) shared task on Automatic Misogyny Identification. We focus on task A —Misogyny and Aggressive Behaviour Identification— which aims at detecting whether a tweet in Italian is misogynous and, if so, whether it is aggressive. Rather than building two different models, one for misogyny and one for aggressiveness identification, we handle the problem as one single multi-label classification task, considering three classes: nonmisogynous, non-aggressive misogynous, and aggressive misogynous. Our threeclass supervised model, built on top of AlBERTo, obtains an overall F1 score of 0.7438 on the task test set (F1 = 0.8102 for the misogyny and F1 = 0.6774 for the aggressiveness task), which outperforms the top submitted model (F1 = 0.7406).1

[1]  Frank Hutter,et al.  Fixing Weight Decay Regularization in Adam , 2017, ArXiv.

[2]  Thamar Solorio,et al.  Aggression and Misogyny Detection using BERT: A Multi-Task Approach , 2020, TRAC.

[3]  S. Chaudhury,et al.  Misogyny, feminism, and sexual harassment , 2017, Industrial psychiatry journal.

[4]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[5]  Paolo Rosso,et al.  Overview of the Task on Automatic Misogyny Identification at IberEval 2018 , 2018, IberEval@SEPLN.

[6]  Giovanni Semeraro,et al.  AlBERTo: Italian BERT Language Understanding Model for NLP Challenging Tasks Based on Tweets , 2019, CLiC-it.

[7]  Elisabetta Fersini,et al.  Unintended Bias in Misogyny Detection , 2019, 2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI).

[8]  Paolo Rosso,et al.  Automatic Identification and Classification of Misogynistic Language on Twitter , 2018, NLDB.

[9]  Marcin Mironczuk,et al.  A recent overview of the state-of-the-art elements of text classification , 2018, Expert Syst. Appl..

[10]  Danilo Croce,et al.  EVALITA 2020: Overview of the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian , 2020, EVALITA.

[11]  Xuanjing Huang,et al.  How to Fine-Tune BERT for Text Classification? , 2019, CCL.

[12]  Valerio Basile,et al.  Long-term Social Media Data Collection at the University of Turin , 2018, CLiC-it.

[13]  Paolo Rosso,et al.  AMI @ EVALITA2020: Automatic Misogyny Identification , 2020, EVALITA.

[14]  Paolo Rosso,et al.  Overview of the Evalita 2018 Task on Automatic Misogyny Identification (AMI) , 2018, EVALITA@CLiC-it.