Stop PropagHate at SemEval-2019 Tasks 5 and 6: Are abusive language classification results reproducible?
TL
TL;DR
This paper summarizes the participation of Stop PropagHate team at SemEval 2019, finding poor results when applying it to the HatEval contest, but proving to have a better performance for offense detection than for hate speech.
Abstract
This paper summarizes the participation of Stop PropagHate team at SemEval 2019. Our approach is based on replicating one of the most relevant works on the literature, using word embeddings and LSTM. After circumventing some of the problems of the original code, we found poor results when applying it to the HatEval contest (F1=0.45). We think this is due mainly to inconsistencies in the data of this contest. Finally, for the OffensEval the classifier performed well (F1=0.74), proving to have a better performance for offense detection than for hate speech.
References30 items
1
SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter
2
SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)
3
Predicting the Type and Target of Offensive Posts in Social Media
4
Comparative Studies of Detecting Abusive Language on Twitter
5