# Abuse Detection on Offensive Dataset

Source: [Abuse Detection on Offensive Dataset](<https://www.sota2.com/research/sota/abuse-detection-on-offensive-dataset>)

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

Data updated: 2026-02-26T05:27:16.884Z

Evaluation of Abuse Detection performance using the Offensive Dataset, measured by AUC, Accuracy, Precision, Recall, and 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 | Abuse Detection |
| Dataset (including any stated split) | Offensive Dataset |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/abuse-detection-on-offensive-dataset.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/abuse-detection-on-offensive-dataset.md?metric=AUC>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/abuse-detection-on-offensive-dataset.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/abuse-detection-on-offensive-dataset.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/abuse-detection-on-offensive-dataset.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DL-Text & Metadata (Interleaved) | 87 | Not recorded | 68fa64121e209131cea02881 |
| DL-Text & Metadata (Tran. Lear. FT) | 86 | Not recorded | 68fa64121e209131cea02881 |
| DL-Text & Metadata (Naive Train.) | 85 | Not recorded | 68fa64121e209131cea02881 |
| DL-Text & Metadata (Tran. Lear.) | 85 | Not recorded | 68fa64121e209131cea02881 |
| DL-Text only | 83 | Not recorded | 68fa64121e209131cea02881 |
| Baseline Naive Bayes | 81 | Not recorded | 68fa64121e209131cea02881 |
| Waseem and Hovy 2016 | 74 | Not recorded | 68fa64121e209131cea02881 |
| DL-Metadata only | 74 | Not recorded | 68fa64121e209131cea02881 |

### DL-Text & Metadata (Interleaved)

Accuracy: 87. Result ID: 698c0b72f729bc7f68e7fb42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

Recorded evaluation configuration: {"Features":"Text & Metadata","Training Strategy":"Interleaved Training"}. This record does not assert independent reproduction.

### DL-Text & Metadata (Tran. Lear. FT)

Accuracy: 86. Result ID: 698c0b72f729bc7f68e7fb41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

Recorded evaluation configuration: {"Features":"Text & Metadata","Training Strategy":"Transfer Learning with Fine-Tuning"}. This record does not assert independent reproduction.

### DL-Text & Metadata (Naive Train.)

Accuracy: 85. Result ID: 698c0b72f729bc7f68e7fb3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

Recorded evaluation configuration: {"Features":"Text & Metadata","Training Strategy":"Naive Training"}. This record does not assert independent reproduction.

### DL-Text & Metadata (Tran. Lear.)

Accuracy: 85. Result ID: 698c0b72f729bc7f68e7fb40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

Recorded evaluation configuration: {"Features":"Text & Metadata","Training Strategy":"Transfer Learning"}. This record does not assert independent reproduction.

### DL-Text only

Accuracy: 83. Result ID: 698c0b72f729bc7f68e7fb3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

Recorded evaluation configuration: {"Features":"Text only"}. This record does not assert independent reproduction.

### Baseline Naive Bayes

Accuracy: 81. Result ID: 698c0b72f729bc7f68e7fb3b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Waseem and Hovy 2016

Accuracy: 74. Result ID: 698c0b72f729bc7f68e7fb3c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DL-Metadata only

Accuracy: 74. Result ID: 698c0b72f729bc7f68e7fb3d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64121e209131cea02881.md>)

Recorded evaluation configuration: {"Features":"Metadata only"}. This record does not assert independent reproduction.

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