Social Media Insights During the COVID-19 Pandemic: Infodemiology Study Using Big Data
Bibliographic record
Abstract
BACKGROUND: The COVID-19 pandemic is still undergoing complicated developments in Vietnam and around the world. There is a lot of information about the COVID-19 pandemic, especially on the internet where people can create and share information quickly. This can lead to an infodemic, which is a challenge every government might face in the fight against pandemics. OBJECTIVE: This study aims to understand public attention toward the pandemic (from December 2019 to November 2020) through 7 types of sources: Facebook, Instagram, YouTube, blogs, news sites, forums, and e-commerce sites. METHODS: We collected and analyzed nearly 38 million pieces of text data from the aforementioned sources via SocialHeat, a social listening (infoveillance) platform developed by YouNet Group. We described not only public attention volume trends, discussion sentiments, top sources, top posts that gained the most public attention, and hot keyword frequency but also hot keywords' co-occurrence as visualized by the VOSviewer software tool. RESULTS: In this study, we reached four main conclusions. First, based on changing discussion trends regarding the COVID-19 subject, 7 periods were identified based on events that can be aggregated into two pandemic waves in Vietnam. Second, community pages on Facebook were the source of the most engagement from the public. However, the sources with the highest average interaction efficiency per article were government sources. Third, people's attitudes when discussing the pandemic have changed from negative to positive emotions. Fourth, the type of content that attracts the most interactions from people varies from time to time. Besides that, the issue-attention cycle theory occurred not only once but four times during the COVID-19 pandemic in Vietnam. CONCLUSIONS: Our study shows that online resources can help the government quickly identify public attention to public health messages during times of crisis. We also determined the hot spots that most interested the public and public attention communication patterns, which can help the government get practical information to make more effective policy reactions to help prevent the spread of the pandemic.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".