SOTAVerified

Sentiment Analysis

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:

Papers

Showing 42014250 of 5630 papers

TitleStatusHype
Tandem Anchoring: a Multiword Anchor Approach for Interactive Topic Modeling0
Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification using Convolutional Neural Network0
Improving Distributed Representations of Tweets - Present and Future0
A Deep Neural Architecture for Sentence-level Sentiment Classification in Twitter Social NetworkingCode0
Explaining Recurrent Neural Network Predictions in Sentiment Analysis0
Stance Detection in Turkish Tweets0
How Important is Syntactic Parsing Accuracy? An Empirical Evaluation on Rule-Based Sentiment Analysis0
Deep Learning for Hate Speech Detection in TweetsCode0
Does the Geometry of Word Embeddings Help Document Classification? A Case Study on Persistent Homology Based Representations0
An Automatic Contextual Analysis and Clustering Classifiers Ensemble approach to Sentiment Analysis0
Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge0
Contextual Explanation NetworksCode0
Multiple Source Domain Adaptation with Adversarial Training of Neural NetworksCode0
TwiInsight: Discovering Topics and Sentiments from Social Media Datasets0
W2VLDA: Almost Unsupervised System for Aspect Based Sentiment AnalysisCode0
Universal Dependencies Parsing for Colloquial Singaporean EnglishCode0
On Identifying Disaster-Related Tweets: Matching-based or Learning-based?Code0
Amobee at SemEval-2017 Task 4: Deep Learning System for Sentiment Detection on Twitter0
On the effectiveness of feature set augmentation using clusters of word embeddings0
Optimizing a PoS Tagset for Norwegian Dependency Parsing0
OMNIRank: Risk Quantification for P2P Platforms with Deep Learning0
Decision Stream: Cultivating Deep Decision TreesCode1
Learning to Skim TextCode0
BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMsCode0
Sentiment analysis based on rhetorical structure theory: Learning deep neural networks from discourse trees0
FEUP at SemEval-2017 Task 5: Predicting Sentiment Polarity and Intensity with Financial Word EmbeddingsCode0
Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning0
What we really want to find by Sentiment Analysis: The Relationship between Computational Models and Psychological State0
NILC-USP at SemEval-2017 Task 4: A Multi-view Ensemble for Twitter Sentiment AnalysisCode0
An Automated Text Categorization Framework based on Hyperparameter OptimizationCode0
Learning to Generate Reviews and Discovering SentimentCode0
Japanese Sentiment Classification using a Tree-Structured Long Short-Term Memory with Attention0
Interpretation of Semantic Tweet RepresentationsCode0
Aligning Entity Names with Online Aliases on Twitter0
The Scope and Focus of Negation: A Complete Annotation Framework for Italian0
Potential and Limitations of Cross-Domain Sentiment Classification0
A Twitter Corpus and Benchmark Resources for German Sentiment Analysis0
Author Profiling at PAN: from Age and Gender Identification to Language Variety Identification (invited talk)0
The BreakingNews Dataset0
Elucidating Conceptual Properties from Word Embeddings0
CAT: Credibility Analysis of Arabic Content on Twitter0
Word Embedding and Topic Modeling Enhanced Multiple Features for Content Linking and Argument / Sentiment Labeling in Online Forums0
Not All Segments are Created Equal: Syntactically Motivated Sentiment Analysis in Lexical Space0
Twitter Language Identification Of Similar Languages And Dialects Without Ground Truth0
Word Sense Filtering Improves Embedding-Based Lexical Substitution0
A Code-Switching Corpus of Turkish-German Conversations0
A Characterization Study of Arabic Twitter Data with a Benchmarking for State-of-the-Art Opinion Mining Models0
Sentiment Analysis and Lexical Cohesion for the Story Cloze Task0
Debunking Sentiment Lexicons: A Case of Domain-Specific Sentiment Classification for Croatian0
Comparison of Short-Text Sentiment Analysis Methods for Croatian0
Show:102550
← PrevPage 85 of 113Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Word+ES (Scratch)Attack Success Rate100Unverified
2MT-DNN-SMARTAccuracy97.5Unverified
3T5-11BAccuracy97.5Unverified
4MUPPET Roberta LargeAccuracy97.4Unverified
5T5-3BAccuracy97.4Unverified
6ALBERTAccuracy97.1Unverified
7StructBERTRoBERTa ensembleAccuracy97.1Unverified
8XLNet (single model)Accuracy97Unverified
9SMARTRoBERTaDev Accuracy96.9Unverified
10ELECTRAAccuracy96.9Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-large with LlamBERTAccuracy96.68Unverified
2RoBERTa-largeAccuracy96.54Unverified
3XLNetAccuracy96.21Unverified
4Heinsen Routing + RoBERTa LargeAccuracy96.2Unverified
5RoBERTa-large 355M + Entailment as Few-shot LearnerAccuracy96.1Unverified
6GraphStarAccuracy96Unverified
7DV-ngrams-cosine with NB sub-sampling + RoBERTa.baseAccuracy95.94Unverified
8DV-ngrams-cosine + RoBERTa.baseAccuracy95.92Unverified
9Roberta_Large ST + Cosine Similarity LossAccuracy95.9Unverified
10BERT large finetune UDAAccuracy95.8Unverified
#ModelMetricClaimedVerifiedStatus
1Llama-3.3-70B + CAPOAccuracy62.27Unverified
2Mistral-Small-24B + CAPOAccuracy 60.2Unverified
3Heinsen Routing + RoBERTa LargeAccuracy59.8Unverified
4RoBERTa-large+Self-ExplainingAccuracy59.1Unverified
5Qwen2.5-32B + CAPOAccuracy 59.07Unverified
6Heinsen Routing + GPT-2Accuracy58.5Unverified
7BCN+Suffix BiLSTM-Tied+CoVeAccuracy56.2Unverified
8BERT LargeAccuracy55.5Unverified
9LM-CPPF RoBERTa-baseAccuracy54.9Unverified
10BCN+ELMoAccuracy54.7Unverified
#ModelMetricClaimedVerifiedStatus
1Char-level CNNError4.88Unverified
2SVDCNNError4.74Unverified
3LEAMError4.69Unverified
4fastText, h=10, bigramError4.3Unverified
5SWEM-hierError4.19Unverified
6SRNNError3.96Unverified
7M-ACNNError3.89Unverified
8DNC+CUWError3.6Unverified
9CCCapsNetError3.52Unverified
10Block-sparse LSTMError3.27Unverified
#ModelMetricClaimedVerifiedStatus
1Millions of EmojiTraining Time1,500Unverified
2VLAWEAccuracy93.3Unverified
3RoBERTa-large 355M + Entailment as Few-shot LearnerAccuracy92.5Unverified
4AnglE-LLaMA-7BAccuracy91.09Unverified
5byte mLSTM7Accuracy86.8Unverified
6MEANAccuracy84.5Unverified
7RNN-CapsuleAccuracy83.8Unverified
8Capsule-BAccuracy82.3Unverified
9SuBiLSTM-TiedAccuracy81.6Unverified
10USE_T+CNNAccuracy81.59Unverified