Deploying Artificial Intelligence to Combat Covid-19 Misinformation on Social Media: Technological and Ethical Considerations
Bibliographic record
Abstract
This paper reports on research into online misinformation pertaining to the COVID-19 pandemic using artificial intelligence. This is part of our longer-term goal, i.e., the development of an artificial intelligence (machine-learning) tool to assist social media platforms, online service providers and government agencies in identifying and responding to misinformation on social media. We report herein on the predictive accuracy accomplished by applying a combination of technologies, including a custom-designed web-crawler, The Dark Crawler (TDC) and the Posit toolkit, a text-reading software solution designed by George Weir of University of Strathclyde. Overall, we found that performance of models based upon Posit-derived textual features showed high levels of correlation to the pre-determined (manual and machine-driven) data classifications. We further argue that the harms associated with COVID-19 misinformation — e.g., the social and economic damage, and the deaths and severe illnesses — outweigh the right to personal privacy and freedom of speech considerations.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.052 | 0.149 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.007 |
| Scholarly communication | 0.009 | 0.011 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".