RuG @ EVALITA 2018: Hate Speech Detection In Italian Social Media

Xiaoyu Bai; Flavio Merenda; Claudia Zaghi; Tomasso Caselli; Malvina Nissim

RuG @ EVALITA 2018: Hate Speech Detection In Italian Social Media

Xiaoyu Bai, Flavio Merenda, Claudia Zaghi, Tomasso Caselli, Malvina Nissim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic

1 Citation (Scopus)

208 Downloads (Pure)

Abstract

We describe the systems the RuG Team developed in the context of the Hate Speech Detection Task in Italian Social Media at EVALITA 2018. We submitted a total of eight runs, participating in all four subtasks. The best macro-F1 score in all subtasks was obtained by a Linear SVM, using hate-rich embeddings. Our best system obtains competitive results, by rank- ing 6th (out of 14) in HaSpeeDe-FB, 3rd (out of 15) in HaSpeeDe-TW, 8th (out of 13) in Cross-HaSpeeDe FB, and 6th (out of 13) in Cross-HaSpeeDe TW.

Original language	English
Title of host publication	Sixth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian
Subtitle of host publication	Final Workshop (EVALITA 2018)
Editors	Tommaso Caselli, Nicole Novielli, Viviana Patti, Paolo Rosso
Publisher	CEUR Workshop Proceedings (CEUR-WS.org)
Number of pages	5
Publication status	Published - 2018
Event	EVALITA 2018 - CLIC-It 2018, Turin, Italy Duration: 12-Dec-2018 → 13-Dec-2018

Workshop

Workshop	EVALITA 2018
Country	Italy
City	Turin
Period	12/12/2018 → 13/12/2018

Keywords

hate speech
word embeddings
benchmark

Access to Document

RuG @ EVALITA 2018: Hate Speech Detection In Italian Social MediaFinal publisher's version, 289 KBLicence: Unspecified

Cite this

Bai, Xiaoyu ; Merenda, Flavio ; Zaghi, Claudia ; Caselli, Tomasso ; Nissim, Malvina. / RuG @ EVALITA 2018 : Hate Speech Detection In Italian Social Media. Sixth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian: Final Workshop (EVALITA 2018). editor / Tommaso Caselli ; Nicole Novielli ; Viviana Patti ; Paolo Rosso. CEUR Workshop Proceedings (CEUR-WS.org), 2018.

@inproceedings{e862d1cb9e5a4c1082bd0c36ed1076c1,

title = "RuG @ EVALITA 2018: Hate Speech Detection In Italian Social Media",

abstract = "We describe the systems the RuG Team developed in the context of the Hate Speech Detection Task in Italian Social Media at EVALITA 2018. We submitted a total of eight runs, participating in all four subtasks. The best macro-F1 score in all subtasks was obtained by a Linear SVM, using hate-rich embeddings. Our best system obtains competitive results, by rank- ing 6th (out of 14) in HaSpeeDe-FB, 3rd (out of 15) in HaSpeeDe-TW, 8th (out of 13) in Cross-HaSpeeDe FB, and 6th (out of 13) in Cross-HaSpeeDe TW.",

keywords = "hate speech, word embeddings, benchmark",

author = "Xiaoyu Bai and Flavio Merenda and Claudia Zaghi and Tomasso Caselli and Malvina Nissim",

year = "2018",

language = "English",

editor = "Tommaso Caselli and Nicole Novielli and Viviana Patti and Paolo Rosso",

booktitle = "Sixth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian",

publisher = "CEUR Workshop Proceedings (CEUR-WS.org)",

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

}

Bai, X, Merenda, F, Zaghi, C, Caselli, T & Nissim, M 2018, RuG @ EVALITA 2018: Hate Speech Detection In Italian Social Media. in T Caselli, N Novielli, V Patti & P Rosso (eds), Sixth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian: Final Workshop (EVALITA 2018). CEUR Workshop Proceedings (CEUR-WS.org), EVALITA 2018, Turin, Italy, 12/12/2018.

RuG @ EVALITA 2018 : Hate Speech Detection In Italian Social Media. / Bai, Xiaoyu; Merenda, Flavio; Zaghi, Claudia; Caselli, Tomasso ; Nissim, Malvina.

Sixth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian: Final Workshop (EVALITA 2018). ed. / Tommaso Caselli; Nicole Novielli; Viviana Patti; Paolo Rosso. CEUR Workshop Proceedings (CEUR-WS.org), 2018.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic

TY - GEN

T1 - RuG @ EVALITA 2018

T2 - EVALITA 2018

AU - Bai, Xiaoyu

AU - Merenda, Flavio

AU - Zaghi, Claudia

AU - Caselli, Tomasso

AU - Nissim, Malvina

PY - 2018

Y1 - 2018

N2 - We describe the systems the RuG Team developed in the context of the Hate Speech Detection Task in Italian Social Media at EVALITA 2018. We submitted a total of eight runs, participating in all four subtasks. The best macro-F1 score in all subtasks was obtained by a Linear SVM, using hate-rich embeddings. Our best system obtains competitive results, by rank- ing 6th (out of 14) in HaSpeeDe-FB, 3rd (out of 15) in HaSpeeDe-TW, 8th (out of 13) in Cross-HaSpeeDe FB, and 6th (out of 13) in Cross-HaSpeeDe TW.

AB - We describe the systems the RuG Team developed in the context of the Hate Speech Detection Task in Italian Social Media at EVALITA 2018. We submitted a total of eight runs, participating in all four subtasks. The best macro-F1 score in all subtasks was obtained by a Linear SVM, using hate-rich embeddings. Our best system obtains competitive results, by rank- ing 6th (out of 14) in HaSpeeDe-FB, 3rd (out of 15) in HaSpeeDe-TW, 8th (out of 13) in Cross-HaSpeeDe FB, and 6th (out of 13) in Cross-HaSpeeDe TW.

KW - hate speech

KW - word embeddings

KW - benchmark

M3 - Conference contribution

BT - Sixth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian

A2 - Caselli, Tommaso

A2 - Novielli, Nicole

A2 - Patti, Viviana

A2 - Rosso, Paolo

PB - CEUR Workshop Proceedings (CEUR-WS.org)

Y2 - 12 December 2018 through 13 December 2018

ER -