SST-3

Stanford Sentiment Treebank: 3-way

Dataset Information
Modalities
Texts
Languages
English
Introduced
2013
License
Apache 2.0
Homepage
Official Website
Contents

Overview

SST-5 is the Stanford Sentiment Treebank 5-way classification dataset (positive, somewhat positive, neutral, somewhat negative, negative). To create SST-3 (positive, neutral, negative), the 'somewhat positive' class was merged and treated as 'positive'. Similarly, the 'somewhat negative' class was merged and treated as 'negative'.

Variants: SST-3

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Sentiment Analysis GPT-4o-mini Fine-Tuned ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis GPT-4o Fine-Tuned (Minimal) ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis GPT-4o + ELECTRA Large FT ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis GPT-4o (Prompt) ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis GPT-4o + ELECTRA Large FT (Prompt, Label, Examples) ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis GPT-4o-mini + ELECTRA Large FT (Prompt, Label, Examples) ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis GPT-4o-mini + ELECTRA Base FT ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis GPT-4o-mini + ELECTRA Large FT (Prompt, Label) ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis ELECTRA Large Fine-Tuned ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis GPT-4o-mini (Prompt) ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29
Sentiment Analysis ELECTRA Base Fine-Tuned ELECTRA and GPT-4o: Cost-Effective Partners … 2024-12-29

Research Papers

Recent papers with results on this dataset:

External Links: