(Mis)Information on Digital Platforms: Quantitative and Qualitative Analysis of Content From Twitter and Sina Weibo in the COVID-19 Pandemic
Bibliographic record
Abstract
Background: Misinformation about COVID-19 on social media has presented challenges to public health authorities during the pandemic. This paper leverages qualitative and quantitative content analysis on cross-platform, cross-national discourse and misinformation in the context of COVID-19. Specifically, we investigated COVID-19-related content on Twitter and Sina Weibo-the largest microblogging sites in the United States and China, respectively. Objective: Using data from 2 prominent microblogging platform, Twitter, based in the United States, and Sina Weibo, based in China, we compared the content and relative prevalence of misinformation to better understand public discourse of public health issues across social media and cultural contexts. Methods: A total of 3,579,575 posts were scraped from both Sina Weibo and Twitter, focusing on content from January 30, 2020, within 24 hours of when WHO declared COVID-19 a "public health emergency of international concern," and a week later, on February 6, 2020. We examined how the use and engagement measured by keyword frequencies and hashtags differ across the 2 platforms. A 1% random sample of tweets that contained both the English keywords "coronavirus" and "covid-19" and the equivalent Chinese characters was extracted and analyzed based on changes in the frequencies of keywords and hashtags and the Viterbi algorithm. We manually coded a random selection of 5%-7% of the content to identify misinformation on each platform and compared posts using the WHO fact-check page to adjudicate accuracy of content. Results: Both platforms posted about the outbreak and transmission, but posts on Sina Weibo were less likely to reference topics such as WHO, Hong Kong, and death and more likely to cite themes of resisting, fighting, and cheering against coronavirus. Misinformation constituted 1.1% of Twitter content and 0.3% of Sina Weibo content-almost 4 times as much on Twitter compared to Sina Weibo. Conclusions: Quantitative and qualitative analysis of content on both platforms points to lower degrees of misinformation, more content designed to bolster morale, and less reference to topics such as WHO, death, and Hong Kong on Sina Weibo than on Twitter.
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".