Temporal and textual analysis of social media on collective discourses during the Zika virus pandemic

An Environmental Uncertainty Perception Framework for Misinformation Detection and Spread Prediction in the COVID-19 Pandemic: Artificial Intelligence Approach

BACKGROUND

Amidst the COVID-19 pandemic, misinformation on social media has posed significant threats to public health. Detecting and predicting the spread of misinformation are crucial for mitigating its adverse effects. However, prevailing frameworks for these tasks have predominantly focused on post-level signals of misinformation, neglecting features of the broader information environment where misinformation originates and proliferates.

OBJECTIVE

This study aims to create a novel framework that integrates the uncertainty of the information environment into misinformation features, with the goal of enhancing the model's accuracy in tasks such as misinformation detection and predicting the scale of dissemination. The objective is to provide better support for online governance efforts during health crises.

METHODS

In this study, we embraced uncertainty features within the information environment and introduced a novel Environmental Uncertainty Perception (EUP) framework for the detection of misinformation and the prediction of its spread on social media. The framework encompasses uncertainty at 4 scales of the information environment: physical environment, macro-media environment, micro-communicative environment, and message framing. We assessed the effectiveness of the EUP using real-world COVID-19 misinformation data sets.

RESULTS

The experimental results demonstrated that the EUP alone achieved notably good performance, with detection accuracy at 0.753 and prediction accuracy at 0.71. These results were comparable to state-of-the-art baseline models such as bidirectional long short-term memory (BiLSTM; detection accuracy 0.733 and prediction accuracy 0.707) and bidirectional encoder representations from transformers (BERT; detection accuracy 0.755 and prediction accuracy 0.728). Additionally, when the baseline models collaborated with the EUP, they exhibited improved accuracy by an average of 1.98% for the misinformation detection and 2.4% for spread-prediction tasks. On unbalanced data sets, the EUP yielded relative improvements of 21.5% and 5.7% in macro-F1-score and area under the curve, respectively.

CONCLUSIONS

This study makes a significant contribution to the literature by recognizing uncertainty features within information environments as a crucial factor for improving misinformation detection and spread-prediction algorithms during the pandemic. The research elaborates on the complexities of uncertain information environments for misinformation across 4 distinct scales, including the physical environment, macro-media environment, micro-communicative environment, and message framing. The findings underscore the effectiveness of incorporating uncertainty into misinformation detection and spread prediction, providing an interdisciplinary and easily implementable framework for the field.

Public health agencies' use of social media for communication during pandemics: a scoping review of the literature

Public health agencies (PHAs) have increasingly incorporated social media into their communication mix during successive pandemics in the 21st century. However, the quality, timing, and accuracy of their health messages have varied significantly, resulting in mixed outcomes for communication, audience engagement, and pandemic management. This study aimed to identify factors influencing the effectiveness of pandemic-related health messages shared by PHAs on social media and to report their impact on public engagement as documented in the literature. A scoping literature review was conducted following a predefined protocol. An electronic search of 7 relevant databases and 5 grey literature repositories yielded 9,714 papers published between January 2003 and November 2022. Seventy-three papers were deemed eligible and selected for review. The results underscored the insufficiency of social media guidance policies for PHAs. Six themes were identified: message source, message topic, message style, message timing, content credibility and reliability, and message recipient profile. These themes encompassed 20 variables that could inform PHAs' social media public health communication during pandemics. Additionally, the findings revealed potential interconnectedness among the variables, and this study concluded by proposing a conceptual model that expands upon existing theoretical foundations for developing and evaluating pandemic-related health messaging.

Deconstructing agency in the G20 leaders' declarations in the last decade: A corpus-assisted discourse study

Investigating agency has become a pivotal issue in discourse studies, especially organizational discourse. This study aims to identify the controlling agency (who/what) behind G20 leaders' declarations in the last decade and how such agency is constructed. To this end, this study offers a concise examination of relevant literature investigating fundamental concepts like discourse and agency in light of the overlapping relationship between form and function in language studies. Further, an eclectic methodological approach has been devised to arrive at a multi-leveled analysis. Two stages of analysis were designed. First, a corpus of the declarations between 2012 and 2021 was created and analyzed using #LancsBox v.6.x. and Wmatrix. At this stage, we was established as a prime agent in the corpus and proven to collocate heavily with agentive speech acts. One sample declaration, Riyadh 2020, was used for minute discourse analysis in the second stage. Inspired by transitivity system, process type analysis, and multivalence frameworks, this stage revealed the profound presence of non-human agency alongside the human one. Nevertheless, further examination demonstrated that this sample still constrains non-human agency due to semantic and textual constraints.

Extracting Feelings of People Regarding COVID-19 by Social Network Mining

In 2020, COVID-19 became one of the most critical concerns in the world. This topic is even still widely discussed on all social networks. Each day, many users publish millions of tweets and comments around this subject, implicitly showing the public’s ideas and points of view regarding this subject. In this regard, to extract the public’s point of view in various countries at the early stages of this outbreak, a dataset of Coronavirus-related tweets in the English language has been collected, which consists of more than two million tweets starting from 23 March until 23 June 2020. To this end, we first use a lexicon-based approach with the GeoNames geographic database to label each tweet with its location. Next, a method based on the recently introduced and widely cited Roberta model is proposed to analyse each tweet’s sentiment. Afterwards, some analysis showing the frequency of the tweets and their sentiments is reported for each country and the world as a whole. We mainly focus on the countries with Coronavirus as a hot topic. Graph analysis shows that the frequency of the tweets for most countries is significantly correlated with the official daily statistics of COVID-19. We also discuss some other extracted knowledge that was implicit in the tweets.

Network Structure and Community Evolution Online: Behavioral and Emotional Changes in Response to COVID-19

Background: The measurement and identification of changes in the social structure in response to an exceptional event like COVID-19 can facilitate a more informed public response to the pandemic and provide fundamental insights on how collective social processes respond to extreme events. Objective: In this study, we built a generalized framework for applying social media data to understand public behavioral and emotional changes in response to COVID-19. Methods: Utilizing a complete dataset of Sina Weibo posts published by users in Wuhan from December 2019 to March 2020, we constructed a time-varying social network of 3.5 million users. In combination with community detection, text analysis, and sentiment analysis, we comprehensively analyzed the evolution of the social network structure, as well as the behavioral and emotional changes across four main stages of Wuhan's experience with the epidemic. Results: The empirical results indicate that almost all network indicators related to the network's size and the frequency of social interactions increased during the outbreak. The number of unique recipients, average degree, and transitivity increased by 24, 23, and 19% during the severe stage than before the outbreak, respectively. Additionally, the similarity of topics discussed on Weibo increased during the local peak of the epidemic. Most people began discussing the epidemic instead of the more varied cultural topics that dominated early conversations. The number of communities focused on COVID-19 increased by nearly 40 percent of the total number of communities. Finally, we find a statistically significant "rebound effect" by exploring the emotional content of the users' posts through paired sample t-test (P = 0.003). Conclusions: Following the evolution of the network and community structure can explain how collective social processes changed during the pandemic. These results can provide data-driven insights into the development of public attention during extreme events.

Learning about COVID-19: a qualitative interview study of Australians' use of information sources

BACKGROUND

A multitude of information sources are available to publics when novel infectious diseases first emerge. In this paper, we adopt a qualitative approach to investigate how Australians learnt about the novel coronavirus and COVID-19 and what sources of information they had found most useful and valuable during the early months of the pandemic.

METHODS

In-depth semi-structured telephone interviews were conducted with a diverse group of 40 Australian adults in mid-2020 about their experiences of the COVID-19 crisis. Participants were recruited through Facebook advertising. Detailed case studies were created for each participant, providing the basis of a thematic analysis which focused on the participants' responses to the questions about COVID-19-related information sources.

RESULTS

Diverse sources of COVID-19-related information, including traditional media, online media and in-person interactions, were actively accessed, appraised and engaged with by participants. There was a high level of interest in COVID-19 information as people grappled with uncertainty, anxiety and feeling overwhelmed. Certain key events or experiences made people become aware that the outbreak was threatening Australia and potentially themselves. Most people demonstrated keen awareness that misinformation was rife in news outlets and social media sites and that they were taking steps to determine the accuracy of information. High trust was placed in health experts, scientists and government sources to provide reliable information. Also important to participants were informal discussions with friends and family members who were experts or working in relevant fields, as well as engaging in-person in interactions and hearing from friends and family who lived overseas about what COVID-19 conditions were like there.

CONCLUSION

A constantly changing news environment raises challenges for effective communication of risk and containment advice. People can become confused, distressed and overwhelmed by the plethora of information sources and fast-changing news environment. On the other hand, seeking out information can provide reassurance and comfort in response to anxiety and uncertainty. Clarity and consistency in risk messaging is important, as is responding quickly to changes in information and misinformation. Further research should seek to identify any changes in use of and trust in information sources as time goes by.