# Sentiment Analysis on FPB (F-1)

Source: [Sentiment Analysis on FPB (F-1)](<https://www.sota2.com/research/sota/sentiment-analysis-on-fpb-f-1>)

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

Data updated: 2026-02-26T05:43:27.291Z

Evaluation of Sentiment Analysis performance on the FPB dataset, measured by F-1 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 | Sentiment Analysis |
| Dataset (including any stated split) | FPB |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/sentiment-analysis-on-fpb-f-1.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| FiLM | 84.48 | Not recorded | 68fa78c81e209131cea7a7bf |
| RoBERTa | 83.93 | Not recorded | 68fa78c81e209131cea7a7bf |
| BERT | 81.73 | Not recorded | 68fa78c81e209131cea7a7bf |
| BloombergGPT | 51.07 | Not recorded | 68fa78c81e209131cea7a7bf |

### FiLM

F1 Score: 84.48. Result ID: 6995a33d3badfaffe6a0569d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bf.md>)

[Implementation](<https://github.com/deep-over/FiLM>)

Recorded evaluation configuration: {"Params":"110M","Training tokens":"2.4B"}. This record does not assert independent reproduction.

### RoBERTa

F1 Score: 83.93. Result ID: 6995a33d3badfaffe6a0569c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bf.md>)

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

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

Recorded evaluation configuration: {"Params":"110M"}. This record does not assert independent reproduction.

### BERT

F1 Score: 81.73. Result ID: 6995a33d3badfaffe6a0569b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Params":"110M"}. This record does not assert independent reproduction.

### BloombergGPT

F1 Score: 51.07. Result ID: 6995a33d3badfaffe6a0569a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c81e209131cea7a7bf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c25.md>)

Recorded evaluation configuration: {"Params":"50B"}. This record does not assert independent reproduction.

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