Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social Media

Tharindu Ranasinghe; Hansi Hettiarachchi

doi:10.26615/978-954-452-056-4_056

Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social Media

Tharindu Ranasinghe
, Hansi Hettiarachchi

Birmingham City University

Research output: Chapter in Book/Published conference output › Conference publication

33 Citations (Scopus)

13 Downloads (Pure)

Abstract

This paper describes a novel research approach to detect type and target of offensive posts in social media using a capsule network. The input to the network was character embeddings combined with emoji embeddings. The approach was evaluated on all three subtasks in Task 6 - SemEval 2019: OffensEval: Identifying and Categorizing Offensive Language in Social Media. The evaluation also showed that even though the capsule networks have not been used commonly in natural language processing tasks, they can outperform existing state of the art solutions for offensive language detection in social media.

Original language	English
Title of host publication	International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Pages	474-480
Number of pages	7
DOIs	https://doi.org/10.26615/978-954-452-056-4_056
Publication status	Published - Sept 2019

Bibliographical note

Access to Document

10.26615/978-954-452-056-4_056Licence: CC BY 4.0

R19-1056
ACL materials are Copyright © 1963–2023 ACL. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
Final published version, 212 KBLicence: CC BY 4.0

Cite this

@inproceedings{01858075426f4ba28cfc3bf47cc2e597,

title = "Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social Media",

abstract = "This paper describes a novel research approach to detect type and target of offensive posts in social media using a capsule network. The input to the network was character embeddings combined with emoji embeddings. The approach was evaluated on all three subtasks in Task 6 - SemEval 2019: OffensEval: Identifying and Categorizing Offensive Language in Social Media. The evaluation also showed that even though the capsule networks have not been used commonly in natural language processing tasks, they can outperform existing state of the art solutions for offensive language detection in social media.",

author = "Tharindu Ranasinghe and Hansi Hettiarachchi",

note = "ACL materials are Copyright {\textcopyright} 1963–2023 ACL. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.",

year = "2019",

month = sep,

doi = "10.26615/978-954-452-056-4\_056",

language = "English",

pages = "474--480",

booktitle = "International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",

}

TY - GEN

T1 - Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social Media

AU - Ranasinghe, Tharindu

AU - Hettiarachchi, Hansi

PY - 2019/9

Y1 - 2019/9

N2 - This paper describes a novel research approach to detect type and target of offensive posts in social media using a capsule network. The input to the network was character embeddings combined with emoji embeddings. The approach was evaluated on all three subtasks in Task 6 - SemEval 2019: OffensEval: Identifying and Categorizing Offensive Language in Social Media. The evaluation also showed that even though the capsule networks have not been used commonly in natural language processing tasks, they can outperform existing state of the art solutions for offensive language detection in social media.

AB - This paper describes a novel research approach to detect type and target of offensive posts in social media using a capsule network. The input to the network was character embeddings combined with emoji embeddings. The approach was evaluated on all three subtasks in Task 6 - SemEval 2019: OffensEval: Identifying and Categorizing Offensive Language in Social Media. The evaluation also showed that even though the capsule networks have not been used commonly in natural language processing tasks, they can outperform existing state of the art solutions for offensive language detection in social media.

UR - https://www.aclweb.org/anthology/R19-1056

U2 - 10.26615/978-954-452-056-4_056

DO - 10.26615/978-954-452-056-4_056

M3 - Conference publication

SP - 474

EP - 480

BT - International Conference on Recent Advances in Natural Language Processing (RANLP 2019)

ER -

Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social Media

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this