HaMor at the Profiling Hate Speech Spreaders on Twitter

Mirko Lai; Marco Antonio Stranisci; Cristina Bosco; Rossana Damiano; Viviana Patti

HaMor at the Profiling Hate Speech Spreaders on Twitter

Mirko Lai
, Marco Antonio Stranisci
, Cristina Bosco
, Rossana Damiano
, Viviana Patti

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper we describe the Hate and Morality (HaMor) submission for the Profiling Hate Speech Spreaders on Twitter task at PAN 2021. We ranked as the 19th position - over 66 participating teams - according to the averaged accuracy value of 73% reached by our proposed models over the two languages. We obtained the 43th higher accuracy for English (62%) and the 2nd higher accuracy for Spanish (84%). We proposed four types of features for inferring users attitudes just from the text in their messages: HS detection, users morality, named entities, and communicative behaviour. The results of our experiments are promising and will lead to future investigations of these features in a finer grained perspective.

Original language	English
Pages (from-to)	2047-2055
Number of pages	9
Journal	CEUR Workshop Proceedings
Volume	2936
Publication status	Published - 2021
Externally published	Yes
Event	22nd Working Notes of CLEF - Conference and Labs of the Evaluation Forum, CLEF-WN 2021 - Virtual, Online, Romania Duration: 21 Sept 2021 → 24 Sept 2021

Keywords

Communicative behaviour
Hate speech
Moral values
Named entities

Cite this

@article{2adeae827a8447e6b802637d446b1919,

title = "HaMor at the Profiling Hate Speech Spreaders on Twitter",

abstract = "In this paper we describe the Hate and Morality (HaMor) submission for the Profiling Hate Speech Spreaders on Twitter task at PAN 2021. We ranked as the 19th position - over 66 participating teams - according to the averaged accuracy value of 73\% reached by our proposed models over the two languages. We obtained the 43th higher accuracy for English (62\%) and the 2nd higher accuracy for Spanish (84\%). We proposed four types of features for inferring users attitudes just from the text in their messages: HS detection, users morality, named entities, and communicative behaviour. The results of our experiments are promising and will lead to future investigations of these features in a finer grained perspective.",

keywords = "Communicative behaviour, Hate speech, Moral values, Named entities",

author = "Mirko Lai and Stranisci, \{Marco Antonio\} and Cristina Bosco and Rossana Damiano and Viviana Patti",

note = "Publisher Copyright: {\textcopyright} 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).; 22nd Working Notes of CLEF - Conference and Labs of the Evaluation Forum, CLEF-WN 2021 ; Conference date: 21-09-2021 Through 24-09-2021",

year = "2021",

language = "English",

volume = "2936",

pages = "2047--2055",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - HaMor at the Profiling Hate Speech Spreaders on Twitter

AU - Lai, Mirko

AU - Stranisci, Marco Antonio

AU - Bosco, Cristina

AU - Damiano, Rossana

AU - Patti, Viviana

PY - 2021

Y1 - 2021

N2 - In this paper we describe the Hate and Morality (HaMor) submission for the Profiling Hate Speech Spreaders on Twitter task at PAN 2021. We ranked as the 19th position - over 66 participating teams - according to the averaged accuracy value of 73% reached by our proposed models over the two languages. We obtained the 43th higher accuracy for English (62%) and the 2nd higher accuracy for Spanish (84%). We proposed four types of features for inferring users attitudes just from the text in their messages: HS detection, users morality, named entities, and communicative behaviour. The results of our experiments are promising and will lead to future investigations of these features in a finer grained perspective.

AB - In this paper we describe the Hate and Morality (HaMor) submission for the Profiling Hate Speech Spreaders on Twitter task at PAN 2021. We ranked as the 19th position - over 66 participating teams - according to the averaged accuracy value of 73% reached by our proposed models over the two languages. We obtained the 43th higher accuracy for English (62%) and the 2nd higher accuracy for Spanish (84%). We proposed four types of features for inferring users attitudes just from the text in their messages: HS detection, users morality, named entities, and communicative behaviour. The results of our experiments are promising and will lead to future investigations of these features in a finer grained perspective.

KW - Communicative behaviour

KW - Hate speech

KW - Moral values

KW - Named entities

UR - https://www.scopus.com/pages/publications/85113537137

M3 - Conference article

AN - SCOPUS:85113537137

SN - 1613-0073

VL - 2936

SP - 2047

EP - 2055

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - 22nd Working Notes of CLEF - Conference and Labs of the Evaluation Forum, CLEF-WN 2021

Y2 - 21 September 2021 through 24 September 2021

ER -

HaMor at the Profiling Hate Speech Spreaders on Twitter

Abstract

Keywords

Other files and links

Fingerprint

Cite this