# Classification on Twitter Natural language (test)

Source: [Classification on Twitter Natural language (test)](<https://www.sota2.com/research/sota/classification-on-twitter-natural-language-test>)

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

Data updated: 2026-02-26T06:09:07.933Z

Evaluation of general classification performance on the test split of the Twitter Natural language dataset, measured using Balanced Accuracy (bACC) and Geometric Mean (GM).

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 | Classification |
| Dataset (including any stated split) | Twitter Natural language (test) |
| Metric | bACC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [bACC](<https://www.sota2.com/research/sota/classification-on-twitter-natural-language-test.md?metric=bACC>): Higher is better; unit: PERCENT.

- [GM](<https://www.sota2.com/research/sota/classification-on-twitter-natural-language-test.md?metric=GM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | bACC | Result date | Report paper |
| --- | --- | --- | --- |
| LDAM + M2m | 78.8 | Not recorded | 68fa68f11e209131cea1f256 |
| ERM + M2m | 78.2 | Not recorded | 68fa68f11e209131cea1f256 |
| LDAM + DRW | 78 | Not recorded | 68fa68f11e209131cea1f256 |
| ERM + DRS | 77.8 | Not recorded | 68fa68f11e209131cea1f256 |
| ERM + CB-RW | 77.5 | Not recorded | 68fa68f11e209131cea1f256 |
| ERM + RW | 76.2 | Not recorded | 68fa68f11e209131cea1f256 |
| ERM + RS | 75.8 | Not recorded | 68fa68f11e209131cea1f256 |
| ERM + SMOTE | 75.8 | Not recorded | 68fa68f11e209131cea1f256 |
| ERM | 74.7 | Not recorded | 68fa68f11e209131cea1f256 |
| LDAM | 74.6 | Not recorded | 68fa68f11e209131cea1f256 |
| Focal | 74.2 | Not recorded | 68fa68f11e209131cea1f256 |

### LDAM + M2m

bACC: 78.8. Result ID: 698d8ec98b517eb4332257d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Implementation](<https://github.com/alinlab/M2m>)

Recorded evaluation configuration: {"Loss":"LDAM","Re-balancing":"M2m","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### ERM + M2m

bACC: 78.2. Result ID: 698d8ec98b517eb4332257d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Implementation](<https://github.com/alinlab/M2m>)

Recorded evaluation configuration: {"Loss":"ERM","Re-balancing":"M2m","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### LDAM + DRW

bACC: 78. Result ID: 698d8ec98b517eb4332257d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Loss":"LDAM","Re-balancing":"DRW","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### ERM + DRS

bACC: 77.8. Result ID: 698d8ec98b517eb4332257d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Loss":"ERM","Re-balancing":"DRS","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### ERM + CB-RW

bACC: 77.5. Result ID: 698d8ec98b517eb4332257cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa654f1e209131cea0988a.md>)

[Implementation](<https://github.com/richardaecn/class-balanced-loss>)

Recorded evaluation configuration: {"Loss":"ERM","Re-balancing":"CB-RW","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### ERM + RW

bACC: 76.2. Result ID: 698d8ec98b517eb4332257ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

Recorded evaluation configuration: {"Loss":"ERM","Re-balancing":"RW","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### ERM + RS

bACC: 75.8. Result ID: 698d8ec98b517eb4332257cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

Recorded evaluation configuration: {"Loss":"ERM","Re-balancing":"RS","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### ERM + SMOTE

bACC: 75.8. Result ID: 698d8ec98b517eb4332257cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60691e209131ce9ef1af.md>)

Recorded evaluation configuration: {"Loss":"ERM","Re-balancing":"SMOTE","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### ERM

bACC: 74.7. Result ID: 698d8ec98b517eb4332257cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

Recorded evaluation configuration: {"Loss":"ERM","Re-balancing":"-","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### LDAM

bACC: 74.6. Result ID: 698d8ec98b517eb4332257d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Loss":"LDAM","Re-balancing":"-","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

### Focal

bACC: 74.2. Result ID: 698d8ec98b517eb4332257d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68f11e209131cea1f256.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa640c1e209131cea02556.md>)

[Implementation](<https://github.com/facebookresearch/Detectron>)

Recorded evaluation configuration: {"Loss":"Focal","Re-balancing":"-","Imbalance ratio":"~147.9"}. This record does not assert independent reproduction.

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