STANCE-C3: Domain-adaptive Cross-target Stance Detection via Contrastive Learning and Counterfactual Generation (preprint)

Stance detection is the process of inferring a person's position or standpoint on a specific issue to deduce prevailing perceptions toward topics of general or controversial interest, such as health policies during the COVID-19 pandemic. Existing models for stance detection are trained to perform well for a single domain (e.g., COVID-19) and a specific target topic (e.g., masking protocols), but are generally ineffectual in other domains or targets due to distributional shifts in the data. However, constructing high-performing, domain-specific stance detection models requires an extensive corpus of labeled data relevant to the targeted domain, yet such datasets are not readily available. This poses a challenge as the process of annotating data is costly and time-consuming. To address these challenges, we introduce a novel stance detection model coined domain-adaptive Cross-target STANCE detection via Contrastive learning and Counterfactual generation (STANCE-C3) that uses counterfactual data augmentation to enhance domain-adaptive training by enriching the target domain dataset during the training process and requiring significantly less information from the new domain. We also propose a modified self-supervised contrastive learning as a component of STANCE-C3 to prevent overfitting for the existing domain and target and enable cross-target stance detection. Through experiments on various datasets, we show that STANCE-C3 shows performance improvement over existing state-of-the-art methods.

Bridging the Gap: Commonality and Differences between Online and Offline COVID-19 Data (preprint)

With the onset of the COVID-19 pandemic, news outlets and social media have become central tools for disseminating and consuming information. Because of their ease of access, users seek COVID-19-related information from online social media (i.e., online news) and news outlets (i.e., offline news). Online and offline news are often connected, sharing common topics while each has unique, different topics. A gap between these two news sources can lead to misinformation propagation. For instance, according to the Guardian, most COVID-19 misinformation comes from users on social media. Without fact-checking social media news, misinformation can lead to health threats. In this paper, we focus on the novel problem of bridging the gap between online and offline data by monitoring their common and distinct topics generated over time. We employ Twitter (online) and local news (offline) data for a time span of two years. Using online matrix factorization, we analyze and study online and offline COVID-19-related data differences and commonalities. We design experiments to show how online and offline data are linked together and what trends they follow.

The in vitro and in vivo potency of CT-P59 against Delta and its associated variants of SARS-CoV-2 (preprint)

The Delta variant originally from India is rapidly spreading across the world and causes to resurge infections of SARS-CoV-2. We previously reported that CT-P59 presented its in vivo potency against Beta and Gamma variants, despite its reduced activity in cell experiments. Yet, it remains uncertain to exert the antiviral effect of CT-P59 on the Delta and its associated variants (L452R). To tackle this question, we carried out cell tests and animal study. CT-P59 showed reduced antiviral activity but enabled neutralization against Delta, Epsilon, and Kappa variants in cells. In line with in vitro results, the mouse challenge experiment with the Delta variant substantiated in vivo potency of CT-P59 showing symptom remission and virus abrogation in the respiratory tract. Collectively, cell and animal studies showed that CT-P59 is effective against the Delta variant infection, hinting that CT-P59 has therapeutic potency for patients infected with Delta and its associated variants.