Answers are grounded in this paper and cite their sources.
Computational study demonstrates high accuracy in detecting manipulated web images and fraudulent media, highlighting the effectiveness of vision transformers against online disinformation.
Significant issues arise from the spread of hate speech and fraudulent data on the internet, especially during times of social and political unrest. To solve these problems, this study suggests a transformer-driven method for identifying bogus data, with an emphasis on how it relates to hate speech. We utilize the Swin Transformer model, which is well-known for its effectiveness in managing vast amounts of image data, to accurately identify and discriminate between authentic and counterfeit information. Our experimental results reveal that our approach is resilient in detecting bogus data, especially when it comes to hate speech, with an accuracy of up to 97.76%. Further evaluation metrics demonstrate our model’s strength: sensitivity at 0.9916, specificity at 0.9615, precision at 0.9672, and an F1 Score of 0.9793. This study makes a substantial advancement in deep learning.
No takes yet. Share an insight, caveat, or question.
Vadhvani et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: