Automatic Identification and Filtration of COVID-19 Misinformation
Bibliographic record
Abstract
The rapid spread of online fake news through some media platforms has increased over the last decade. Misinformation and disinformation of any kind is extensively propagated through social media platforms, some of the popular ones are Facebook and Twitter. With the present global pandemic ravaging the world and killing hundreds of thousands, getting fake news from these social media platforms can exacerbate the situation. Unfortunately, there has been a lot of misinformation and disinformation on COVID-19 virus implications of which has been disastrous for various people, countries, and economies. The right information is crucial in the fight against this pandemic and, in this age of data explosion, where TBs of data is generated every minute, near real time identification and tagging of misinformation is quintessential to minimize its consequences. In this paper, the authors use Natural Language Processing (NLP) based two-step approach to classify a tweet to be a potentially misinforming one or not. Firstly, COVID -19 tagged tweets were filtered based on the presence of keywords formulated from the list of common misinformation spread around the virus. Secondly, a deep neural network (RNN) trained on openly available real and fake news dataset was used to predict if the keyword filtered tweets were factual or misinformed.
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 | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.002 |
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".