Sentiment Analysis

1277 papers with code • 43 benchmarks • 92 datasets

Sentiment Analysis is the task of classifying the polarity of a given text. For instance, a text-based tweet can be categorized into either "positive", "negative", or "neutral". Given the text and accompanying labels, a model can be trained to predict the correct sentiment.

Sentiment Analysis techniques can be categorized into machine learning approaches, lexicon-based approaches, and even hybrid methods. Some subcategories of research in sentiment analysis include: multimodal sentiment analysis, aspect-based sentiment analysis, fine-grained opinion analysis, language specific sentiment analysis.

More recently, deep learning techniques, such as RoBERTa and T5, are used to train high-performing sentiment classifiers that are evaluated using metrics like F1, recall, and precision. To evaluate sentiment analysis systems, benchmark datasets like SST, GLUE, and IMDB movie reviews are used.

Further readings:

Libraries

Use these libraries to find Sentiment Analysis models and implementations
10 papers
123,180
5 papers
2,548
See all 6 libraries.

Most implemented papers

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.

Character-level Convolutional Networks for Text Classification

makcedward/nlpaug NeurIPS 2015

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification.

Distributed Representations of Sentences and Documents

inejc/paragraph-vectors 16 May 2014

Its construction gives our algorithm the potential to overcome the weaknesses of bag-of-words models.

Universal Sentence Encoder

facebookresearch/InferSent 29 Mar 2018

For both variants, we investigate and report the relationship between model complexity, resource consumption, the availability of transfer task training data, and task performance.

XLNet: Generalized Autoregressive Pretraining for Language Understanding

zihangdai/xlnet 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.

Pay Attention to MLPs

labmlai/annotated_deep_learning_paper_implementations NeurIPS 2021

Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years.

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

google-research/electra 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.

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

stanfordnlp/treelstm IJCNLP 2015

Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks.

A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

HKUST-KnowComp/R-Net NeurIPS 2016

Recent results at the intersection of Bayesian modelling and deep learning offer a Bayesian interpretation of common deep learning techniques such as dropout.

EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks

jasonwei20/eda_nlp IJCNLP 2019

We present EDA: easy data augmentation techniques for boosting performance on text classification tasks.