# Sentiment Analysis on IMDB, Amazon, Yelp, and TweetEval Average

Source: [Sentiment Analysis on IMDB, Amazon, Yelp, and TweetEval Average](<https://www.sota2.com/research/sota/sentiment-analysis-on-imdb-amazon-yelp-and-tweeteval-average>)

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

Data updated: 2026-02-26T05:35:13.814Z

Average performance of Sentiment Analysis models across the IMDB, Amazon, Yelp, and TweetEval datasets, typically measured by 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 Analysis |
| Dataset (including any stated split) | IMDB, Amazon, Yelp, and TweetEval Overall Average |
| Metric | Average Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Average Accuracy](<https://www.sota2.com/research/sota/sentiment-analysis-on-imdb-amazon-yelp-and-tweeteval-average.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| IMO-BART | 91.81 | Not recorded | 68fa72f91e209131cea59b4c |
| IMO-BART last | 90.49 | Not recorded | 68fa72f91e209131cea59b4c |
| CHATGPT | 88.66 | Not recorded | 68fa72f91e209131cea59b4c |
| ALPACA-7B | 88.52 | Not recorded | 68fa72f91e209131cea59b4c |
| PDA | 88.51 | Not recorded | 68fa72f91e209131cea59b4c |
| PADA | 87.78 | Not recorded | 68fa72f91e209131cea59b4c |
| BART | 86.8 | Not recorded | 68fa72f91e209131cea59b4c |
| BERT-EDA | 86.69 | Not recorded | 68fa72f91e209131cea59b4c |
| BERT-UDA | 86.31 | Not recorded | 68fa72f91e209131cea59b4c |
| BERT-PGB | 86.11 | Not recorded | 68fa72f91e209131cea59b4c |
| ALPACA-7B-LORA | 85.34 | Not recorded | 68fa72f91e209131cea59b4c |
| BERT | 84.87 | Not recorded | 68fa72f91e209131cea59b4c |
| IMO-BART B2T | 73.33 | Not recorded | 68fa72f91e209131cea59b4c |
| IMO-BART w/o sq | 71.93 | Not recorded | 68fa72f91e209131cea59b4c |

### IMO-BART

Average Accuracy: 91.81. Result ID: 6992a6413a6c314849106546.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Implementation](<https://github.com/WilliamsToTo/IMO>)

Recorded evaluation configuration: {"Backbone":"BART"}. This record does not assert independent reproduction.

### IMO-BART last

Average Accuracy: 90.49. Result ID: 6992a6413a6c314849106549.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Implementation](<https://github.com/WilliamsToTo/IMO>)

Recorded evaluation configuration: {"Backbone":"BART","Masking":"last layer only"}. This record does not assert independent reproduction.

### CHATGPT

Average Accuracy: 88.66. Result ID: 6992a6413a6c314849106543.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Model":"gpt-3.5-turbo","Evaluation protocol":"Few-shot in-context learning"}. This record does not assert independent reproduction.

### ALPACA-7B

Average Accuracy: 88.52. Result ID: 6992a6413a6c314849106544.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 7B","Tuning":"fine-tuned"}. This record does not assert independent reproduction.

### PDA

Average Accuracy: 88.51. Result ID: 6992a6413a6c314849106542.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

Recorded evaluation configuration: {"Approach":"Prompt learning"}. This record does not assert independent reproduction.

### PADA

Average Accuracy: 87.78. Result ID: 6992a6413a6c314849106541.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bb31e209131cea2fa81.md>)

Recorded evaluation configuration: {"Approach":"Prompt learning"}. This record does not assert independent reproduction.

### BART

Average Accuracy: 86.8. Result ID: 6992a6413a6c31484910653d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66921e209131cea10fff.md>)

Recorded evaluation configuration: {"Tuning":"fine-tuned"}. This record does not assert independent reproduction.

### BERT-EDA

Average Accuracy: 86.69. Result ID: 6992a6413a6c31484910653e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66421e209131cea0f41a.md>)

Recorded evaluation configuration: {"Data augmentation":"EDA"}. This record does not assert independent reproduction.

### BERT-UDA

Average Accuracy: 86.31. Result ID: 6992a6413a6c31484910653f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a61e209131cea1d69a.md>)

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

Recorded evaluation configuration: {"Data augmentation":"UDA"}. This record does not assert independent reproduction.

### BERT-PGB

Average Accuracy: 86.11. Result ID: 6992a6413a6c314849106540.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb21e209131cea41888.md>)

Recorded evaluation configuration: {"Data augmentation":"PGB"}. This record does not assert independent reproduction.

### ALPACA-7B-LORA

Average Accuracy: 85.34. Result ID: 6992a6413a6c314849106545.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 7B","Tuning":"LoRA fine-tuned"}. This record does not assert independent reproduction.

### BERT

Average Accuracy: 84.87. Result ID: 6992a6413a6c31484910653c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

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

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

Recorded evaluation configuration: {"Tuning":"fine-tuned"}. This record does not assert independent reproduction.

### IMO-BART B2T

Average Accuracy: 73.33. Result ID: 6992a6413a6c314849106547.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Implementation](<https://github.com/WilliamsToTo/IMO>)

Recorded evaluation configuration: {"Backbone":"BART","Search strategy":"bottom-up layer-wise search"}. This record does not assert independent reproduction.

### IMO-BART w/o sq

Average Accuracy: 71.93. Result ID: 6992a6413a6c314849106548.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59b4c.md>)

[Implementation](<https://github.com/WilliamsToTo/IMO>)

Recorded evaluation configuration: {"Backbone":"BART","Search strategy":"simultaneous search"}. This record does not assert independent reproduction.

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