Comparing Different Supervised Approaches to Hate Speech Detection

Michele Corazza; Stefano Menini; Pinar Arslan; Rachele Sprugnoli; Elena Cabrio; Sara Tonelli; Serena Villata

Comparing Different Supervised Approaches to Hate Speech Detection

Michele Corazza, Stefano Menini, Pinar Arslan, Rachele Sprugnoli, Elena Cabrio, Sara Tonelli, Serena Villata

Università Cattolica del Sacro Cuore

Risultato della ricerca: Contributo in libro › Contributo a convegno

1 Citazioni (Scopus)

Abstract

This paper reports on the systems the InriaFBK Team submitted to the EVALITA 2018 - Shared Task on Hate Speech Detection in Italian Twitter and Facebook posts (HaSpeeDe). Our submissions were based on three separate classes of models: a model using a recurrent layer, an ngram-based neural network and a LinearSVC. For the Facebook task and the two cross-domain tasks we used the recurrent model and obtained promising results, especially in the cross-domain setting. For Twitter, we used an ngram-based neural network and the LinearSVC-based model.

Lingua originale	English
Titolo della pubblicazione ospite	Proceedings of the Sixth Evaluation Campaign of Natural Language processing and Speech Tools for Italian (EVALITA 2018)
Pagine	230-234
Numero di pagine	5
Stato di pubblicazione	Pubblicato - 2018
Evento	EVALITA 2018 - Torino, Italy Durata: 12 dic 2018 → 13 dic 2018

Workshop

Workshop	EVALITA 2018
Città	Torino, Italy
Periodo	12/12/18 → 13/12/18

Keywords

hate speech detection, information extraction, Italian

Altri file e collegamenti

Cita questo

@inproceedings{d4dbed863c6c45db959e37a495b8aff1,

title = "Comparing Different Supervised Approaches to Hate Speech Detection",

abstract = "This paper reports on the systems the InriaFBK Team submitted to the EVALITA 2018 - Shared Task on Hate Speech Detection in Italian Twitter and Facebook posts (HaSpeeDe). Our submissions were based on three separate classes of models: a model using a recurrent layer, an ngram-based neural network and a LinearSVC. For the Facebook task and the two cross-domain tasks we used the recurrent model and obtained promising results, especially in the cross-domain setting. For Twitter, we used an ngram-based neural network and the LinearSVC-based model.",

keywords = "hate speech detection, information extraction, Italian, hate speech detection, information extraction, Italian",

author = "Michele Corazza and Stefano Menini and Pinar Arslan and Rachele Sprugnoli and Elena Cabrio and Sara Tonelli and Serena Villata",

year = "2018",

language = "English",

isbn = "978-88-31978-42-2",

pages = "230--234",

booktitle = "Proceedings of the Sixth Evaluation Campaign of Natural Language processing and Speech Tools for Italian (EVALITA 2018)",

note = "EVALITA 2018 ; Conference date: 12-12-2018 Through 13-12-2018",

}

TY - GEN

T1 - Comparing Different Supervised Approaches to Hate Speech Detection

AU - Corazza, Michele

AU - Menini, Stefano

AU - Arslan, Pinar

AU - Sprugnoli, Rachele

AU - Cabrio, Elena

AU - Tonelli, Sara

AU - Villata, Serena

PY - 2018

Y1 - 2018

N2 - This paper reports on the systems the InriaFBK Team submitted to the EVALITA 2018 - Shared Task on Hate Speech Detection in Italian Twitter and Facebook posts (HaSpeeDe). Our submissions were based on three separate classes of models: a model using a recurrent layer, an ngram-based neural network and a LinearSVC. For the Facebook task and the two cross-domain tasks we used the recurrent model and obtained promising results, especially in the cross-domain setting. For Twitter, we used an ngram-based neural network and the LinearSVC-based model.

AB - This paper reports on the systems the InriaFBK Team submitted to the EVALITA 2018 - Shared Task on Hate Speech Detection in Italian Twitter and Facebook posts (HaSpeeDe). Our submissions were based on three separate classes of models: a model using a recurrent layer, an ngram-based neural network and a LinearSVC. For the Facebook task and the two cross-domain tasks we used the recurrent model and obtained promising results, especially in the cross-domain setting. For Twitter, we used an ngram-based neural network and the LinearSVC-based model.

KW - hate speech detection, information extraction, Italian

UR - http://hdl.handle.net/10807/133051

UR - http://ceur-ws.org/vol-2263/paper039.pdf

M3 - Conference contribution

SN - 978-88-31978-42-2

SP - 230

EP - 234

BT - Proceedings of the Sixth Evaluation Campaign of Natural Language processing and Speech Tools for Italian (EVALITA 2018)

T2 - EVALITA 2018

Y2 - 12 December 2018 through 13 December 2018

ER -

Comparing Different Supervised Approaches to Hate Speech Detection

Abstract

Workshop

Keywords

Altri file e collegamenti

Fingerprint

Cita questo