Activity Trajectory Generation via Modeling Spatiotemporal Dynamics

Human daily activities, such as working, eating out, and traveling, play an essential role in contact tracing and modeling the diffusion patterns of the COVID-19 pandemic. However, individual-level activity data collected from real scenarios are highly limited due to privacy issues and commercial concerns. In this paper, we present a novel framework based on generative adversarial imitation learning, to generate artificial activity trajectories that retain both the fidelity and utility of the real-world data. To tackle the inherent randomness and sparsity of irregular-sampled activities, we innovatively capture the spatiotemporal dynamics underlying trajectories by leveraging neural differential equations. We incorporate the dynamics of continuous flow between consecutive activities and instantaneous updates at observed activity points in temporal evolution and spatial transformation. Extensive experiments on two real-world datasets show that our proposed framework achieves superior performance over state-of-the-art baselines in terms of improving the data fidelity and data utility in facilitating practical applications. Moreover, we apply the synthetic data to model the COVID-19 spreading, and it achieves better performance by reducing the simulation MAPE over the baseline by more than 50%. The source code is available online: https://github.com/tsinghua-fib-lab/Activity-Trajectory-Generation. © 2022 ACM.

D-FEND: A Diffusion-Based Fake News Detection Framework for News Articles Related to COVID-19

The social confusion caused by the recent pandemic of COVID-19 has been further facilitated by fake news diffused via social media on the Internet. For this reason, many studies have been proposed to detect fake news as early as possible. The content-based detection methods consider the difference between the contents of true and fake news articles. However, they suffer from the two serious limitations: (1) the publisher can manipulate the content of a news article easily, and (2) the content depends upon the language, with which the article is written. To overcome these limitations, the diffusion-based fake news detection methods have been proposed. The diffusion-based methods consider the difference among the diffusion patterns of true and fake news articles on social media. Despite its success, however, the lack of the diffusion information regarding to the COVID-19 related fake news prevents from studying the diffusion-based fake news detection methods. Therefore, for overcoming the limitation, we propose a diffusion-based fake news detection framework (D-FEND), which consists of four components: (C1) diffusion data collection, (C2) analysis of the data and feature extraction, (C3) model training, and (C4) inference. Our work contributes to the effort to mitigate the risk of infodemics during a pandemic by (1) building a new diffusion dataset, named CoAID+, (2) identifying and addressing the class imbalance problem of CoAID+, and (3) demonstrating that D-FEND successfully detects fake news articles with 88.89% model accuracy on average. © 2022 ACM.

From #jobsearch to #mask: Improving COVID-19 cascade prediction with spillover effects

An information outbreak occurs on social media along with the COVID-19 pandemic and leads to infodemic. Predicting the popularity of online content, known as cascade prediction, allows for not only catching in advance hot information that deserves attention, but also identifying false information that will widely spread and require quick response to mitigate its impact. Among the various information diffusion patterns leveraged in previous works, the spillover effect of the information exposed to users on their decision to participate in diffusing certain information is still not studied. In this paper, we focus on the diffusion of information related to COVID-19 preventive measures. Through our collected Twitter dataset, we validated the existence of this spillover effect. Building on the finding, we proposed extensions to three cascade prediction methods based on Graph Neural Networks (GNNs). Experiments conducted on our dataset demonstrated that the use of the identified spillover effect significantly improves the state-of-the-art GNNs methods in predicting the popularity of not only preventive measure messages, but also other COVID-19 related messages. © 2021 Owner/Author.