# Informative Tweet Identification on WNUT Task 2 2020 (CV)

Source: [Informative Tweet Identification on WNUT Task 2 2020 (CV)](<https://www.sota2.com/research/sota/informative-tweet-identification-on-wnut-task-2-2020-cv>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:43:03.304Z

Evaluation of Informative Tweet Identification performance on the WNUT Task 2 2020 (CV) dataset, measured by F1-score.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Informative Tweet Identification |
| Dataset (including any stated split) | WNUT Task 2 2020 (CV) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [F1 Score](<https://www.sota2.com/research/sota/informative-tweet-identification-on-wnut-task-2-2020-cv.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| COVID-Twitter-BERT Adv. + ROBERTa Large Adv. | 96.55 | Not recorded | 68fa68831e209131cea1c922 |
| COVID-Twitter-BERT + ROBERTa Large | 96.36 | Not recorded | 68fa68831e209131cea1c922 |
| COVID-Twitter-BERT Adv. | 96.32 | Not recorded | 68fa68831e209131cea1c922 |
| COVID-Twitter-BERT | 96.22 | Not recorded | 68fa68831e209131cea1c922 |
| ROBERTa Large Adv. | 95.78 | Not recorded | 68fa68831e209131cea1c922 |
| ROBERTa Large | 95.6 | Not recorded | 68fa68831e209131cea1c922 |

### COVID-Twitter-BERT Adv. + ROBERTa Large Adv.

F1 Score: 96.55. Result ID: 698d73e58b517eb433219e4f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Implementation](<https://github.com/kpriyanshu256/WNUT-2020-Task-2>)

Recorded evaluation configuration: {"ensemble":true,"adversarial\_training":true}. This record does not assert independent reproduction.

### COVID-Twitter-BERT + ROBERTa Large

F1 Score: 96.36. Result ID: 698d73e58b517eb433219e4e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Implementation](<https://github.com/kpriyanshu256/WNUT-2020-Task-2>)

Recorded evaluation configuration: {"ensemble":true,"adversarial\_training":false}. This record does not assert independent reproduction.

### COVID-Twitter-BERT Adv.

F1 Score: 96.32. Result ID: 698d73e58b517eb433219e4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Implementation](<https://github.com/kpriyanshu256/WNUT-2020-Task-2>)

Recorded evaluation configuration: {"adversarial\_training":true}. This record does not assert independent reproduction.

### COVID-Twitter-BERT

F1 Score: 96.22. Result ID: 698d73e58b517eb433219e4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67881e209131cea16bc2.md>)

Recorded evaluation configuration: {"adversarial\_training":false}. This record does not assert independent reproduction.

### ROBERTa Large Adv.

F1 Score: 95.78. Result ID: 698d73e58b517eb433219e4d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Implementation](<https://github.com/kpriyanshu256/WNUT-2020-Task-2>)

Recorded evaluation configuration: {"adversarial\_training":true}. This record does not assert independent reproduction.

### ROBERTa Large

F1 Score: 95.6. Result ID: 698d73e58b517eb433219e4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"adversarial\_training":false}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
