Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Sentiment Classification research benchmarks – Page 3 · SOTA2 Research

Sentiment Classification

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

83.42F1 Score

18

Feb 26, 2026

Static + 950 auto

90.62Accuracy

18

Feb 26, 2026

82.4Accuracy

18

Feb 26, 2026

SemEval 2017 (OOD)

82.39Accuracy

18

Feb 26, 2026

IMDb (In-domain)

93.23Accuracy

18

Feb 26, 2026

Yelp Full (test)

35.28Test Error

18

Feb 26, 2026

92.3Accuracy

17

Feb 26, 2026

SemEval Twitter Sentiment Analysis 2016 (test)

0.648Avg F1 Score

17

Feb 26, 2026

SemEval Twitter Sentiment Analysis 2015 (test)

68.8Average F1

17

Feb 26, 2026

SemEval Twitter Sentiment Analysis 2014 (test)

0.748Avg F1 Score

17

Feb 26, 2026

SemEval Twitter Sentiment Analysis 2013 (test)

Previous best historical scores

72.8Average F1

17

Feb 26, 2026

Amazon Polarity (test)

4.28Test Error

17

Feb 26, 2026

Unsupervised + Supervised Majority Voting (J-48, SVM, NB)

0.912Accuracy

16

Feb 26, 2026

93.96Accuracy

16

Feb 26, 2026

Random Prompting

68.2Accuracy (de)

16

Feb 26, 2026

Stanford Sentiment Treebank SST-5 (test)

BCN + Char + ELMo

54.7Accuracy

16

Apr 21, 2026

68.5Accuracy

15

Feb 26, 2026

6.27Error Rate

15

Feb 26, 2026

Explicit Ensemble

93.2Accuracy

14

Mar 19, 2026

CR (10-fold cross-validation)

86.3Accuracy

13

Feb 27, 2026

MR (10-fold cross-validation)

83.1Accuracy

13

Feb 27, 2026

SemEval Laptop (test)

Dependency Parser + Recurrent NN

76.15Accuracy

13

Feb 26, 2026

SemEval Restaurant (test)

Dependency Parser + Recurrent NN

0.809Accuracy

13

Feb 26, 2026

82.54Accuracy

13

Jun 26, 2026

90.71Accuracy

13

Jun 11, 2026

Page 3 of 10

Popular datasets

IMDB SST Yelp Amazon Amazon Review

Follow for updates

Join SOTA2 Contact