A multi-modal dataset for hate speech detection on social media: case-study of Russia-Ukraine conflict

Surendrabikram Thapa; Aditya Shah; Farhan Ahmad Jafri; Usman Naseem; Imran Razzak

doi:10.18653/v1/2022.case-1.1

A multi-modal dataset for hate speech detection on social media: case-study of Russia-Ukraine conflict

Surendrabikram Thapa, Aditya Shah, Farhan Ahmad Jafri, Usman Naseem, Imran Razzak

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

24 Citations (Scopus)

Abstract

Hate speech consists of types of content (e.g. text, audio, image) that express derogatory sentiments and hate against certain people or groups of individuals. The internet, particularly social media and microblogging sites, have become an increasingly popular platform for expressing ideas and opinions. Hate speech is prevalent in both offline and online media. A substantial proportion of this kind of content is presented in different modalities (e.g. text, image, video). Taking into account that hate speech spreads quickly during political events, we present a novel multimodal dataset composed of 5680 text-image pairs of tweets data related to the Russia-Ukraine war and annotated with a binary class: "hate" or "no-hate" The baseline results show that multimodal resources are relevant to leverage the hateful information from different types of data. The baselines and dataset provided in this paper may boost researchers in direction of multimodal hate speech, mainly during serious conflicts such as war contexts.

Original language	English
Title of host publication	Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE)
Place of Publication	Stroudsburg
Publisher	Association for Computational Linguistics
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781959429050
DOIs	https://doi.org/10.18653/v1/2022.case-1.1
Publication status	Published - 2022
Externally published	Yes
Event	5th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2022 - Abu Dhabi, United Arab Emirates Duration: 7 Dec 2022 → 8 Dec 2022

Conference

Conference	5th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2022
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	7/12/22 → 8/12/22

Access to Document

10.18653/v1/2022.case-1.1Licence: Unspecified

Cite this

Thapa, S., Shah, A., Jafri, F. A., Naseem, U., & Razzak, I. (2022). A multi-modal dataset for hate speech detection on social media: case-study of Russia-Ukraine conflict. In Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE) (pp. 1-6). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.case-1.1

Thapa, Surendrabikram ; Shah, Aditya ; Jafri, Farhan Ahmad et al. / A multi-modal dataset for hate speech detection on social media : case-study of Russia-Ukraine conflict. Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE). Stroudsburg : Association for Computational Linguistics, 2022. pp. 1-6

@inproceedings{2abbac4888054edd96e652859d062703,

title = "A multi-modal dataset for hate speech detection on social media: case-study of Russia-Ukraine conflict",

abstract = "Hate speech consists of types of content (e.g. text, audio, image) that express derogatory sentiments and hate against certain people or groups of individuals. The internet, particularly social media and microblogging sites, have become an increasingly popular platform for expressing ideas and opinions. Hate speech is prevalent in both offline and online media. A substantial proportion of this kind of content is presented in different modalities (e.g. text, image, video). Taking into account that hate speech spreads quickly during political events, we present a novel multimodal dataset composed of 5680 text-image pairs of tweets data related to the Russia-Ukraine war and annotated with a binary class: {"}hate{"} or {"}no-hate{"} The baseline results show that multimodal resources are relevant to leverage the hateful information from different types of data. The baselines and dataset provided in this paper may boost researchers in direction of multimodal hate speech, mainly during serious conflicts such as war contexts.",

author = "Surendrabikram Thapa and Aditya Shah and Jafri, {Farhan Ahmad} and Usman Naseem and Imran Razzak",

year = "2022",

doi = "10.18653/v1/2022.case-1.1",

language = "English",

pages = "1--6",

booktitle = "Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE)",

publisher = "Association for Computational Linguistics",

note = "5th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2022 ; Conference date: 07-12-2022 Through 08-12-2022",

}

Thapa, S, Shah, A, Jafri, FA, Naseem, U & Razzak, I 2022, A multi-modal dataset for hate speech detection on social media: case-study of Russia-Ukraine conflict. in Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE). Association for Computational Linguistics, Stroudsburg, pp. 1-6, 5th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2022, Abu Dhabi, United Arab Emirates, 7/12/22. https://doi.org/10.18653/v1/2022.case-1.1

A multi-modal dataset for hate speech detection on social media: case-study of Russia-Ukraine conflict. / Thapa, Surendrabikram; Shah, Aditya; Jafri, Farhan Ahmad et al.
Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE). Stroudsburg: Association for Computational Linguistics, 2022. p. 1-6.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - A multi-modal dataset for hate speech detection on social media

T2 - 5th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2022

AU - Thapa, Surendrabikram

AU - Shah, Aditya

AU - Jafri, Farhan Ahmad

AU - Naseem, Usman

AU - Razzak, Imran

PY - 2022

Y1 - 2022

N2 - Hate speech consists of types of content (e.g. text, audio, image) that express derogatory sentiments and hate against certain people or groups of individuals. The internet, particularly social media and microblogging sites, have become an increasingly popular platform for expressing ideas and opinions. Hate speech is prevalent in both offline and online media. A substantial proportion of this kind of content is presented in different modalities (e.g. text, image, video). Taking into account that hate speech spreads quickly during political events, we present a novel multimodal dataset composed of 5680 text-image pairs of tweets data related to the Russia-Ukraine war and annotated with a binary class: "hate" or "no-hate" The baseline results show that multimodal resources are relevant to leverage the hateful information from different types of data. The baselines and dataset provided in this paper may boost researchers in direction of multimodal hate speech, mainly during serious conflicts such as war contexts.

AB - Hate speech consists of types of content (e.g. text, audio, image) that express derogatory sentiments and hate against certain people or groups of individuals. The internet, particularly social media and microblogging sites, have become an increasingly popular platform for expressing ideas and opinions. Hate speech is prevalent in both offline and online media. A substantial proportion of this kind of content is presented in different modalities (e.g. text, image, video). Taking into account that hate speech spreads quickly during political events, we present a novel multimodal dataset composed of 5680 text-image pairs of tweets data related to the Russia-Ukraine war and annotated with a binary class: "hate" or "no-hate" The baseline results show that multimodal resources are relevant to leverage the hateful information from different types of data. The baselines and dataset provided in this paper may boost researchers in direction of multimodal hate speech, mainly during serious conflicts such as war contexts.

UR - http://www.scopus.com/inward/record.url?scp=85143439410&partnerID=8YFLogxK

U2 - 10.18653/v1/2022.case-1.1

DO - 10.18653/v1/2022.case-1.1

M3 - Conference proceeding contribution

AN - SCOPUS:85143439410

SP - 1

EP - 6

BT - Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE)

PB - Association for Computational Linguistics

CY - Stroudsburg

Y2 - 7 December 2022 through 8 December 2022

ER -

Thapa S, Shah A, Jafri FA, Naseem U, Razzak I. A multi-modal dataset for hate speech detection on social media: case-study of Russia-Ukraine conflict. In Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE). Stroudsburg: Association for Computational Linguistics. 2022. p. 1-6 doi: 10.18653/v1/2022.case-1.1

A multi-modal dataset for hate speech detection on social media: case-study of Russia-Ukraine conflict

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this