Sentiment Analysis

Edit

701 papers with code • 32 benchmarks • 60 datasets

Sentiment analysis is the task of classifying the polarity of a given text.

Benchmarks

Add a Result

Dataset	Best Model	Paper Title	Compare
SST-2 Binary classification	SMART-RoBERTa Large	SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization	See all
IMDb	NB-weighted-BON + dv-cosine	Sentiment Classification Using Document Embeddings Trained with Cosine Similarity	See all
SST-5 Fine-grained classification	RoBERTa-large+Self-Explaining	Self-Explaining Structures Improve NLP Models	See all
Yelp Binary classification	XLNet	XLNet: Generalized Autoregressive Pretraining for Language Understanding	See all
Yelp Fine-grained classification	XLNet	XLNet: Generalized Autoregressive Pretraining for Language Understanding	See all
MR	EFL	Entailment as Few-Shot Learner	See all
Amazon Review Polarity	BERT large	Unsupervised Data Augmentation for Consistency Training	See all
Amazon Review Full	BERT large	Unsupervised Data Augmentation for Consistency Training	See all
User and product information	BiLSTM+CHIM	Rethinking Attribute Representation and Injection for Sentiment Classification	See all
CR	EFL	Entailment as Few-Shot Learner	See all
SemEval 2014 Task 4 Subtask 1+2	GRACE	GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis	See all
TweetEval	BERTweet	BERTweet: A pre-trained language model for English Tweets	See all
Multi-Domain Sentiment Dataset	UDALM: Unsupervised Domain Adaptation through Language Modeling	UDALM: Unsupervised Domain Adaptation through Language Modeling	See all
MPQA	EFL	Entailment as Few-Shot Learner	See all
SemEval 2017 Task 4-A	LSTMs+CNNs ensemble with multiple conv. ops	BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs	See all
DBRD	RobBERT v2	RobBERT: a Dutch RoBERTa-based Language Model	See all
Twitter	AEN-BERT	Attentional Encoder Network for Targeted Sentiment Classification	See all
FiQA	FinBERT	FinBERT: Financial Sentiment Analysis with Pre-trained Language Models	See all
RuSentiment	RuBERT-RuSentiment	Deep Transfer Learning Baselines for Sentiment Analysis in Russian	See all
SemEval	LSTMs+CNNs ensemble with multiple conv. ops	BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs	See all
Sogou News	fastText, h=10, bigram	Bag of Tricks for Efficient Text Classification	See all
ASTD	CNN-LSTM	Mazajak: An Online Arabic Sentiment Analyser	See all
ArSAS	CNN-LSTM	Mazajak: An Online Arabic Sentiment Analyser	See all
ChnSentiCorp Dev	RoBERTa-wwm-ext-large	Pre-Training with Whole Word Masking for Chinese BERT	See all
ChnSentiCorp	RoBERTa-wwm-ext-large	Pre-Training with Whole Word Masking for Chinese BERT	See all
Financial PhraseBank	FinBERT	FinBERT: Financial Sentiment Analysis with Pre-trained Language Models	See all
HARD	AraBERTv1	AraBERT: Transformer-based Model for Arabic Language Understanding	See all
AJGT	AraBERTv1	AraBERT: Transformer-based Model for Arabic Language Understanding	See all
LABR (2-class, unbalanced)	AraBERTv1	AraBERT: Transformer-based Model for Arabic Language Understanding	See all
20 Newsgroups	Emotive Lexicon	ASTD: Arabic Sentiment Tweets Dataset	See all
Latvian Twitter Eater Sentiment Dataset	Naive Bayes	What Can We Learn From Almost a Decade of Food Tweets	See all
DynaSent	SVM	Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM	See all

Show all 32 benchmarks

Collapse benchmarks

Datasets

Subtasks

Aspect Sentiment Triplet Extraction

Arabic Sentiment Analysis

target-oriented opinion words extraction

Aspect-oriented Opinion Extraction

Aspect Term Extraction and Sentiment Classification

Fine-Grained Opinion Analysis

Persian Sentiment Analysis

Aspect-Sentiment-Opinion Triplet Extraction

Vietnamese Aspect-Based Sentiment Analysis

Vietnamese Sentiment Analysis

Greatest papers with code

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

tensorflow/models • • NAACL 2019

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.

Ranked #1 on Question Answering on CoQA

Common Sense Reasoning Conversational Response Selection +6

70,698

Paper
Code

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

tensorflow/models • • ICLR 2020

Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not.

Ranked #7 on Question Answering on Quora Question Pairs

Language Modelling Natural Language Understanding +2

70,697

Paper
Code

Adversarial Training Methods for Semi-Supervised Text Classification

tensorflow/models • • 25 May 2016

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting.

Ranked #13 on Sentiment Analysis on IMDb

General Classification Semi Supervised Text Classification +3

70,697

Paper
Code

Effective Use of Word Order for Text Categorization with Convolutional Neural Networks

tensorflow/models • • HLT 2015

Convolutional neural network (CNN) is a neural network that can make use of the internal structure of data such as the 2D structure of image data.

Ranked #18 on Sentiment Analysis on IMDb

General Classification Sentiment Analysis

70,696

Paper
Code

DeBERTa: Decoding-enhanced BERT with Disentangled Attention

huggingface/transformers • • ICLR 2021

Recent progress in pre-trained neural language models has significantly improved the performance of many natural language processing (NLP) tasks.

Ranked #1 on Named Entity Recognition on CoNLL 2003 NER dev

Common Sense Reasoning Coreference Resolution +9

48,862

Paper
Code

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

huggingface/transformers • • NeurIPS 2019

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains challenging.

Ranked #9 on Semantic Textual Similarity on MRPC

Hate Speech Detection Knowledge Distillation +7

48,862

Paper
Code

RoBERTa: A Robustly Optimized BERT Pretraining Approach

huggingface/transformers • • 26 Jul 2019

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging.

Ranked #2 on Common Sense Reasoning on SWAG

Common Sense Reasoning Language Modelling +6

48,862

Paper
Code

XLNet: Generalized Autoregressive Pretraining for Language Understanding

huggingface/transformers • • NeurIPS 2019

With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling.

Ranked #1 on Sentiment Analysis on Yelp Binary classification

Document Ranking Humor Detection +7

48,862

Paper
Code

SqueezeBERT: What can computer vision teach NLP about efficient neural networks?

huggingface/transformers • • 19 Jun 2020

Humans read and write hundreds of billions of messages every day.

Ranked #19 on Natural Language Inference on RTE

Linguistic Acceptability Natural Language Inference +2

36,726

Paper
Code

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

google-research/bert • • ICLR 2020

Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training.

Knowledge Distillation Language Modelling +2

28,616

Paper
Code

Sentiment Analysis Edit

Benchmarks Add a Result

Datasets

Subtasks

Greatest papers with code

Sentiment Analysis

Edit

Benchmarks

Add a Result