Multimodal zero-shot hateful meme detection

Facebook has recently launched the hateful meme detection challenge, which garnered much attention in academic and industry research communities. Researchers have proposed multimodal deep learning classification methods to perform hateful meme detection. While the proposed methods have yielded promi...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHU, Jiawen, LEE, Roy Ka-Wei, CHONG, Wen Haw
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8257
https://ink.library.smu.edu.sg/context/sis_research/article/9260/viewcontent/Multimodal_Zero_Shot_Hateful_Meme_Detection.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9260
record_format dspace
spelling sg-smu-ink.sis_research-92602023-11-10T08:58:39Z Multimodal zero-shot hateful meme detection ZHU, Jiawen LEE, Roy Ka-Wei CHONG, Wen Haw Facebook has recently launched the hateful meme detection challenge, which garnered much attention in academic and industry research communities. Researchers have proposed multimodal deep learning classification methods to perform hateful meme detection. While the proposed methods have yielded promising results, these classification methods are mostly supervised and heavily rely on labeled data that are not always available in the real-world setting. Therefore, this paper explores and aims to perform hateful meme detection in a zero-shot setting. Working towards this goal, we propose Target-Aware Multimodal Enhancement (TAME), which is a novel deep generative framework that can improve existing hateful meme classification models’ performance in detecting unseen types of hateful memes. We conduct extensive experiments on the Facebook hateful meme dataset, and the results show that TAME can significantly improve the state-of-the-art hateful meme classification methods’ performance in seen and unseen settings. 2022-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8257 info:doi/10.1145/3501247.3531557 https://ink.library.smu.edu.sg/context/sis_research/article/9260/viewcontent/Multimodal_Zero_Shot_Hateful_Meme_Detection.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Hateful memes Multimodal Social media mining Artificial Intelligence and Robotics Databases and Information Systems Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Hateful memes
Multimodal
Social media mining
Artificial Intelligence and Robotics
Databases and Information Systems
Graphics and Human Computer Interfaces
spellingShingle Hateful memes
Multimodal
Social media mining
Artificial Intelligence and Robotics
Databases and Information Systems
Graphics and Human Computer Interfaces
ZHU, Jiawen
LEE, Roy Ka-Wei
CHONG, Wen Haw
Multimodal zero-shot hateful meme detection
description Facebook has recently launched the hateful meme detection challenge, which garnered much attention in academic and industry research communities. Researchers have proposed multimodal deep learning classification methods to perform hateful meme detection. While the proposed methods have yielded promising results, these classification methods are mostly supervised and heavily rely on labeled data that are not always available in the real-world setting. Therefore, this paper explores and aims to perform hateful meme detection in a zero-shot setting. Working towards this goal, we propose Target-Aware Multimodal Enhancement (TAME), which is a novel deep generative framework that can improve existing hateful meme classification models’ performance in detecting unseen types of hateful memes. We conduct extensive experiments on the Facebook hateful meme dataset, and the results show that TAME can significantly improve the state-of-the-art hateful meme classification methods’ performance in seen and unseen settings.
format text
author ZHU, Jiawen
LEE, Roy Ka-Wei
CHONG, Wen Haw
author_facet ZHU, Jiawen
LEE, Roy Ka-Wei
CHONG, Wen Haw
author_sort ZHU, Jiawen
title Multimodal zero-shot hateful meme detection
title_short Multimodal zero-shot hateful meme detection
title_full Multimodal zero-shot hateful meme detection
title_fullStr Multimodal zero-shot hateful meme detection
title_full_unstemmed Multimodal zero-shot hateful meme detection
title_sort multimodal zero-shot hateful meme detection
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/8257
https://ink.library.smu.edu.sg/context/sis_research/article/9260/viewcontent/Multimodal_Zero_Shot_Hateful_Meme_Detection.pdf
_version_ 1783955658910990336