ABSTRACT
Social media platforms have become a vital source of information during the outbreak of the pandemic (COVID-19). The phenomena of fake information or news spread through social media have become increasingly prevalent and a powerful tool for information proliferation. Detecting fake news is crucial for the betterment of society. Existing fake news detection models focus on increasing the performance which leads to overfitting and lag generalizability. Hence, these models require training for various datasets of the same domain with significant variations in the distribution. In our work, we have addressed this overfitting issue by designing a robust distribution generalization of transformers-based generative adversarial network (RDGT-GAN) architecture, which can generalize the model for COVID-19 fake news datasets with different distributions without retraining. Based on our experimental findings, it is evident that the proposed model outperforms the current state-of-the-art (SOTA) models in terms of performance.
ABSTRACT
We study how digital crowdfunding platforms can help replenish the sudden economic deficiencies that accompany a global crisis. Specifically, we examine whether public schools, which suffered severe setbacks during the COVID-19 crisis, were able to generate support from online fundraising communities. We study how the shutdown of schools and the shift to online learning in the United States affected private fundraising on the DonorsChoose.org platform. We find evidence that, after the exogenous shock caused by stay-at-home orders, donations to schools increased and the increased level of concern moves toward high-need schools. Moreover, we find a shift in donation patterns, wherein donors swiftly adapted to renewed priorities and redistributed their resources to immediate needs around digital learning infrastructure. Our findings reveal the pivotal role digital platforms can play in facilitating community resilience during times of crisis. © 2022 IEEE Computer Society. All rights reserved.