ABSTRACT
With over 127 million cases globally, the COVID-19 pandemic marks a sentinel event in global health. However, true case estimations have been elusive due to lack of testing and diagnostic capacity, asymptomatic cases, and individuals who do not get tested or seek care. Concomitantly, new digital surveillance tools to detect, characterize, and report COVID-19 cases are emerging, including using structured and unstructured data from users self-reporting COVID-19-related experiences on the Internet and social media platforms. In this study, we develop and evaluate a hybrid unsupervised and supervised machine learning approach to detect self-reported COVID-19-related symptoms on Twitter during the early stages of the pandemic. Tweets were collected from the public API stream from March 3rd-31st 2020, filtered for COVID-19-related terms. We used the biterm topic model to cluster tweets into theme-associated groups for the first 18 days of tweets, which were then extracted and manually annotated to identify users self-reporting suspected COVID-19 symptoms or status. Using this manually annotated data as a training set, we used an XLNet deep learning model for classifying symptom-related tweets from a larger corpus and also evaluated model performance. From 4, 492, 954 tweets collected, the unsupervised learning process yielded 3, 465 (<1%) symptom tweets used to form our ground-truth COVID-19 symptoms dataset (n = 11, 550). The XLNet text classifier achieved the highest accuracy (.91) and f1 (.62) compared to baseline models evaluated for classification. After re-training with adjusted loss function, we boosted the classifier's precision to 0.81 while maintaining a high f1 (0.66), resulting in identification of an additional 2, 622 symptom-related tweets when applied to an additional 11 days of tweets collected. Our study used a hybrid machine learning approach to enable high precision identification of Twitter user-generated COVID-19 symptom discussions. The model is a digital epidemiology tool that can identify social media users who self-report symptoms during the early periods of an outbreak. © 2021 IEEE.
ABSTRACT
This study investigates the types of misinformation spread on Twitter that evokes scientific authority or evidence when making false claims about the antimalarial drug hydroxychloroquine as a treatment for COVID-19. Specifically, we examined tweets generated after former U.S. President Donald Trump retweeted misinformation about the drug using an unsupervised machine learning approach called the biterm topic model that is used to cluster tweets into misinformation topics based on textual similarity. The top 10 tweets from each topic cluster were content coded for three types of misinformation categories related to scientific authority: medical endorsements of hydroxychloroquine, scientific information used to support hydroxychloroquine’s use, and a comparison group that included scientific evidence opposing hydroxychloroquine’s use. Results show a much higher volume of tweets featuring medical endorsements and use of supportive scientific information compared to accurate and updated scientific evidence, that misinformation-related tweets propagated for a longer time frame, and the majority of hydroxychloroquine Twitter discourse expressed positive views about the drug. Metadata from Twitter accounts found that prominent users within misinformation discourse were more likely to have media or political affiliation and explicitly expressed support for President Trump. Conversely, prominent accounts within the scientific opposition discourse primarily consisted of medical doctors or scientists but had far less influence in the Twitter discourse. Implications of these findings and connections to related social media research are discussed, as well as cognitive mechanisms for understanding susceptibility to misinformation and strategies to combat misinformation spread via online platforms. © The Author(s) 2021.