English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Internet memes have become a dominant method of communication; at the sametime, however, they are also increasingly being used to advocate extremism andfoster derogatory beliefs. Nonetheless, we do not have a firm understanding asto which perceptual aspects of memes cause this phenomenon. In this work, weassess the efficacy of current state-of-the-art multimodal machine learningmodels toward hateful meme detection, and in particular with respect to theirgeneralizability across platforms. We use two benchmark datasets comprising12,140 and 10,567 images from 4chan's "Politically Incorrect" board (/pol/) andFacebook's Hateful Memes Challenge dataset to train the competition'stop-ranking machine learning models for the discovery of the most prominentfeatures that distinguish viral hateful memes from benign ones. We conductthree experiments to determine the importance of multimodality onclassification performance, the influential capacity of fringe Web communitieson mainstream social platforms and vice versa, and the models' learningtransferability on 4chan memes. Our experiments show that memes' imagecharacteristics provide a greater wealth of information than its textualcontent. We also find that current systems developed for online detection ofhate speech in memes necessitate further concentration on its visual elementsto improve their interpretation of underlying cultural connotations, implyingthat multimodal models fail to adequately grasp the intricacies of hate speechin memes and generalize across social media platforms.

Feels Bad Man: Dissecting Automated Hateful Meme Detection Through the Lens of Facebook's Challenge