# Sentiment Classification on CivilComments HELM

Source: [Sentiment Classification on CivilComments HELM](<https://www.sota2.com/research/sota/sentiment-classification-on-civilcomments-helm>)

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

Data updated: 2026-02-26T05:37:30.999Z

Evaluation of Sentiment Classification performance on the Civil Comments dataset as defined within the HELM framework, typically measured using Balanced Classification Accuracy.

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 | Sentiment Classification |
| Dataset (including any stated split) | CivilComments HELM |
| Metric | Balanced Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [Balanced Acc](<https://www.sota2.com/research/sota/sentiment-classification-on-civilcomments-helm.md?metric=Balanced%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Balanced Acc | Result date | Report paper |
| --- | --- | --- | --- |
| S-StackingNet | 65.81 | Not recorded | 6993f5f59ebc499c974099b1 |
| U-StackingNet | 65.8 | Not recorded | 6993f5f59ebc499c974099b1 |
| LAA | 65.46 | Not recorded | 6993f5f59ebc499c974099b1 |
| Dawid-Skene | 65.24 | Not recorded | 6993f5f59ebc499c974099b1 |
| EBCC | 65.21 | Not recorded | 6993f5f59ebc499c974099b1 |
| Base-Best | 65.12 | Not recorded | 6993f5f59ebc499c974099b1 |
| M-MSR | 64.98 | Not recorded | 6993f5f59ebc499c974099b1 |
| GLAD | 64.92 | Not recorded | 6993f5f59ebc499c974099b1 |
| LA | 64.86 | Not recorded | 6993f5f59ebc499c974099b1 |
| KOS | 64.84 | Not recorded | 6993f5f59ebc499c974099b1 |
| SML | 64.84 | Not recorded | 6993f5f59ebc499c974099b1 |
| WAwA | 64.79 | Not recorded | 6993f5f59ebc499c974099b1 |
| ZenCrowd | 64.75 | Not recorded | 6993f5f59ebc499c974099b1 |
| Voting | 64.39 | Not recorded | 6993f5f59ebc499c974099b1 |
| PM | 64.3 | Not recorded | 6993f5f59ebc499c974099b1 |
| MACE | 64.13 | Not recorded | 6993f5f59ebc499c974099b1 |
| Base-Worst | 50.91 | Not recorded | 6993f5f59ebc499c974099b1 |
| Logistic Regression | 50 | Not recorded | 6993f5f59ebc499c974099b1 |

### S-StackingNet

Balanced Acc: 65.81. Result ID: 699a7b975698665ec40507c0.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

Recorded evaluation configuration: {"Mode":"Supervised"}. This record does not assert independent reproduction.

### U-StackingNet

Balanced Acc: 65.8. Result ID: 699a7b975698665ec40507be.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

Recorded evaluation configuration: {"Mode":"Unsupervised"}. This record does not assert independent reproduction.

### LAA

Balanced Acc: 65.46. Result ID: 699a7b975698665ec40507ba.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### Dawid-Skene

Balanced Acc: 65.24. Result ID: 699a7b975698665ec40507b3.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### EBCC

Balanced Acc: 65.21. Result ID: 699a7b975698665ec40507bb.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### Base-Best

Balanced Acc: 65.12. Result ID: 699a7b975698665ec40507b0.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### M-MSR

Balanced Acc: 64.98. Result ID: 699a7b975698665ec40507b4.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a11e209131cea1d402.md>)

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

### GLAD

Balanced Acc: 64.92. Result ID: 699a7b975698665ec40507b6.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### LA

Balanced Acc: 64.86. Result ID: 699a7b975698665ec40507b9.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### KOS

Balanced Acc: 64.84. Result ID: 699a7b975698665ec40507b7.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### SML

Balanced Acc: 64.84. Result ID: 699a7b975698665ec40507b8.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### WAwA

Balanced Acc: 64.79. Result ID: 699a7b975698665ec40507b2.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### ZenCrowd

Balanced Acc: 64.75. Result ID: 699a7b975698665ec40507bd.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### Voting

Balanced Acc: 64.39. Result ID: 699a7b975698665ec40507b1.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### PM

Balanced Acc: 64.3. Result ID: 699a7b975698665ec40507bc.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### MACE

Balanced Acc: 64.13. Result ID: 699a7b975698665ec40507b5.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### Base-Worst

Balanced Acc: 50.91. Result ID: 699a7b975698665ec40507af.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

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

### Logistic Regression

Balanced Acc: 50. Result ID: 699a7b975698665ec40507bf.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5f59ebc499c974099b1.md>)

Recorded evaluation configuration: {"Mode":"Supervised"}. This record does not assert independent reproduction.

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