Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup

In the real-world application of COVID-19 misinformation detection, a fundamental challenge is the lack of the labeled COVID data to enable supervised end-to-end training of the models, especially at the early stage of the pandemic. To address this challenge, we propose an unsupervised domain adaptation framework using contrastive learning and adversarial domain mixup to transfer the knowledge from an existing source data domain to the target COVID-19 data domain. In particular, to bridge the gap between the source domain and the target domain, our method reduces a radial basis function (RBF) based discrepancy between these two domains. Moreover, we leverage the power of domain adversarial examples to establish an intermediate domain mixup, where the latent representations of the input text from both domains could be mixed during the training process. Extensive experiments on multiple real-world datasets suggest that our method can effectively adapt misinformation detection systems to the unseen COVID-19 target domain with significant improvements compared to the state-of-the-art baselines. © 2022 IEEE.

[Analysis on the infection source of the first local cluster epidemic caused by the VOC/Gamma variant of SARS-CoV-2 in China].

Objective: To investigate a SARS-CoV-2 epidemic reported in Rongcheng City, Weihai, Shandong Province. Methods: The SARS-CoV-2 nucleic acid positive patients and their close contacts were investigated, and the whole genome sequencing and genetic evolution analysis of 9 variant viruses were carried out. An infection source investigation and analysis were carried out from two sources of home and abroad, and three aspects of human, material and environment. Results: A total of 15 asymptomatic infections were reported in this epidemic, including 13 cases as employees of workshop of aquatic products processing company, with an infection rate of 21.67% (13/60). Two cases were infected people's neighbors in the same village (conjugal relation). The first six positive persons were processing workers engaged in the first process of removing squid viscera in the workshop of the company. The nucleic acid Ct value of the first time were concentrated between 15 and 29, suggesting that the virus load was high, which was suspected to be caused by one-time homologous exposure. The whole genome sequence of 9 SARS-CoV-2 strains was highly homologous, belonging to VOC/Gamma (Lineage P.1.15). No highly homologous sequences were found from previous native and imported cases in China. It was highly homologous with the six virus sequences sampled from May 5 to 26, 2021 uploaded by Chile. The infection source investigation showed that the company had used the squid raw materials captured in the ocean near Chile and Argentina from May to June 2021 over the last 14 days. Many samples of raw materials, products and their outer packages in the inventory were tested positive for nucleic acid. Conclusion: This epidemic is the first local epidemic caused by the VOC/Gamma of SARS-CoV-2 in China. It is speculated that the VOC/Gamma, which was prevalent in South America from May to June 2021, could be imported into China through frozen squid.

Contrastive Domain Adaptation for Early Misinformation Detection: A Case Study on COVID-19

Despite recent progress in improving the performance of misinformation detection systems, classifying misinformation in an unseen domain remains an elusive challenge. To address this issue, a common approach is to introduce a domain critic and encourage domain-invariant input features. However, early misinformation often demonstrates both conditional and label shifts against existing misinformation data (e.g., class imbalance in COVID-19 datasets), rendering such methods less effective for detecting early misinformation. In this paper, we propose contrastive adaptation network for early misinformation detection (CANMD). Specifically, we leverage pseudo labeling to generate high-confidence target examples for joint training with source data. We additionally design a label correction component to estimate and correct the label shifts (i.e., class priors) between the source and target domains. Moreover, a contrastive adaptation loss is integrated in the objective function to reduce the intra-class discrepancy and enlarge the inter-class discrepancy. As such, the adapted model learns corrected class priors and an invariant conditional distribution across both domains for improved estimation of the target data distribution. To demonstrate the effectiveness of the proposed CANMD, we study the case of COVID-19 early misinformation detection and perform extensive experiments using multiple real-world datasets. The results suggest that CANMD can effectively adapt misinformation detection systems to the unseen COVID-19 target domain with significant improvements compared to the state-of-the-art baselines. © 2022 ACM.

[Thoughts and suggestions on co-administration of seasonal influenza vaccine and COVID-19 vaccine].

In the context of the global pandemic of COVID-19, the epidemic intensity, epidemic characteristics and infection risk of influenza have presented new features. COVID-19 and influenza have simultaneously emerged in many regions of the world. COVID-19 and influenza are similar in terms of transmission mode, clinical symptoms and other aspects. There are also similarities in the mechanism of influenza virus and novel coronavirus on cells. At the same time, it is feasible and significant to do a good job in the prevention and control of COVID-19 and influenza. This paper discusses the relevant strategies and measures for the joint prevention and control of influenza and novel coronavirus from the aspects of influenza vaccination to prevent co-infection, simultaneous vaccination of influenza vaccine and novel coronavirus vaccine, etc., and puts forward corresponding thoughts and suggestions, in order to provide scientific support for the formulation of strategies on seasonal influenza vaccine and novel coronavirus vaccination.

A Privacy-aware Distributed Knowledge Graph Approach to QoIS-driven COVID-19 Misinformation Detection

In this paper, we focus on the quality of information service (QoIS) of COVID-19-related information on social media. Our goal is to provide reliable COVID-19 information service by accurately detecting the misleading COVID-19 posts on social media by exploring the community-contributed COVID-19 fact data (CCFD) from different social media platforms. In particular, CCFD refers to the fact-checking reports that are submitted to each social media platform by its users and fact-checking professionals. Our work is motivated by the observation that CCFD often contains useful COVID-19 knowledge facts (e.g., "COVID-19 is not a flu") that can effectively facilitate the identification of misleading COVID-19 social media posts. However, CCFD is often private to the individual social media platform that owns it due to the data privacy concerns such as data copyright of CCFD and user profile information of CCFD contributors. In this paper, we leverage the CCFD from different social media platforms to accurately detect COVID19 misinformation while effectively protecting the privacy of CCFD. Two critical challenges exist in solving our problem: 1) how to generate privacy-aware COVID-19 knowledge facts from the platform-specific CCFD? 2) How to effectively integrate the privacy-aware COVID-19 knowledge facts from different social media platforms to correctly assess the truthfulness of a COVID19 post? To address these challenges, we develop CoviDKG, a COVID-19 distributed knowledge graph framework that constructs a set of CCFD-based knowledge graphs on individual social media platform and exchanges the privacy-aware COVID19 knowledge facts across different platforms to effectively detect misleading COVID-19 posts. We evaluate CoviDKG on two real-world social media datasets and the results show that CoviDKG achieves significant performance gains compared to state-of-the-art baselines in accurately detecting misleading COVID-19 posts on social media. © 2022 IEEE.

A Duo-generative Approach to Explainable Multimodal COVID-19 Misinformation Detection

This paper focuses on a critical problem of explainable multimodal COVID-19 misinformation detection where the goal is to accurately detect misleading information in multimodal COVID-19 news articles and provide the reason or evidence that can explain the detection results. Our work is motivated by the lack of judicious study of the association between different modalities (e.g., text and image) of the COVID-19 news content in current solutions. In this paper, we present a generative approach to detect multimodal COVID-19 misinformation by investigating the cross-modal association between the visual and textual content that is deeply embedded in the multimodal news content. Two critical challenges exist in developing our solution: 1) how to accurately assess the consistency between the visual and textual content of a multimodal COVID-19 news article? 2) How to effectively retrieve useful information from the unreliable user comments to explain the misinformation detection results? To address the above challenges, we develop a duo-generative explainable misinformation detection (DGExplain) framework that explicitly explores the cross-modal association between the news content in different modalities and effectively exploits user comments to detect and explain misinformation in multimodal COVID-19 news articles. We evaluate DGExplain on two real-world multimodal COVID-19 news datasets. Evaluation results demonstrate that DGExplain significantly outperforms state-of-the-art baselines in terms of the accuracy of multimodal COVID-19 misinformation detection and the explainability of detection explanations. © 2022 ACM.

A Multimodal Misinformation Detector for COVID-19 Short Videos on TikTok

This paper studies an emerging and important problem of identifying misleading COVID-19 short videos where the misleading content is jointly expressed in the visual, audio, and textual content of videos. Existing solutions for misleading video detection mainly focus on the authenticity of videos or audios against AI algorithms (e.g., deepfake) or video manipulation, and are insufficient to address our problem where most videos are user-generated and intentionally edited. Two critical challenges exist in solving our problem: i) how to effectively extract information from the distractive and manipulated visual content in TikTok videos? ii) How to efficiently aggregate heterogeneous information across different modalities in short videos? To address the above challenges, we develop TikTec, a multimodal misinformation detection framework that explicitly exploits the captions to accurately capture the key information from the distractive video content, and effectively learns the composed misinformation that is jointly conveyed by the visual and audio content. We evaluate TikTec on a real-world COVID- 19 video dataset collected from TikTok. Evaluation results show that TikTec achieves significant performance gains compared to state-of-the-art baselines in accurately detecting misleading COVID-19 short videos. © 2021 IEEE.