Towards resource inequities in catching the “dark side” of social media: A hateful meme classification framework for low-resource scenarios

Simple item page
dc.contributor.authorLi, Yuming
dc.contributor.authorChan, Johnny
dc.contributor.authorPeko, Gabrielle
dc.contributor.authorSundaram, David
dc.date.accessioned2023-12-26T18:53:00Z
dc.date.available2023-12-26T18:53:00Z
dc.date.issued2024-01-03
dc.identifier.doi10.24251/HICSS.2024.865
dc.identifier.isbn978-0-9981331-7-1
dc.identifier.otherdbb811c7-1b8e-4bb5-b694-7d1a2402d870
dc.identifier.urihttps://hdl.handle.net/10125/107251
dc.language.isoeng
dc.relation.ispartofProceedings of the 57th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectThe Bright and Dark Side of Social Media in the Marginalized Contexts
dc.subjectdata augmentation
dc.subjectdeep learning
dc.subjecthateful meme classification
dc.subjectknowledge distillation
dc.subjectlow- resource nlp
dc.titleTowards resource inequities in catching the “dark side” of social media: A hateful meme classification framework for low-resource scenarios
dc.typeConference Paper
dc.type.dcmiText
dcterms.abstractThe increasing prevalence of social media platforms has led to the emergence of multimodal information such as memes. Hateful memes poses a risk by perpetuating discrimination, reinforcing stereotypes, and causing online harassment, thereby marginalising certain groups and impeding efforts towards inclusivity and social justice. Detecting hateful memes is crucial for creating a safe and equitable online environment. However, existing research heavily relies on complex and large deep learning models, requiring substantial computational resources for training. This creates a barrier for under-resourced researchers and small companies, limiting their participation in hateful information detection and exacerbating inequalities in the field of artificial intelligence. This paper attempts to tackle the problem by proposing a low-resource- oriented framework of hateful meme classification to address limitations in training data, computing power, and modality integration. Our approach achieves faster performance with reduced computational requirements, while maintaining a 94.7% accuracy comparable to the existing highest-scoring model.
dcterms.extent10 pages
prism.startingpage7215

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0705.pdf
Size:
548.09 KB
Format:
Adobe Portable Document Format
Download

Collections

The Bright and Dark Side of Social Media in the Marginalized Contexts