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 55015550 of 5630 papers

TitleStatusHype
Proceedings of the 2nd Workshop on Sentiment Analysis where AI meets Psychology0
Affect Proxies and Ontological Change: A finance case study0
Emotiphons: Emotion Markers in Conversational Speech - Comparison across Indian Languages0
A Pilot Study of Hindustani Music Sentiments0
Combining Social Cognitive Theories with Linguistic Features for Multi-genre Sentiment Analysis0
Chinese Sentiments on the Clouds: A Preliminary Experiment on Corpus Processing and Exploration on Cloud Service0
Emotional Tendency Identification for Micro-blog Topics Based on Multiple Characteristics0
Emotion Estimation from Sentence Using Relation between Japanese Slangs and Emotion Expressions0
Annotation Scheme for Constructing Sentiment Corpus in Korean0
領域相關詞彙極性分析及文件情緒分類之研究 (Domain Dependent Word Polarity Analysis for Sentiment Classification) [In Chinese]0
Unifying Local and Global Agreement and Disagreement Classification in Online Debates0
Prior versus Contextual Emotion of a Word in a Sentence0
Opinum: statistical sentiment analysis for opinion classification0
Sentimantics: Conceptual Spaces for Lexical Sentiment Polarity Representation with Contextuality0
Automatically Annotating A Five-Billion-Word Corpus of Japanese Blogs for Affect and Sentiment Analysis0
Proceedings of the 3rd Workshop in Computational Approaches to Subjectivity and Sentiment Analysis0
On the Impact of Sentiment and Emotion Based Features in Detecting Online Sexual Predators0
Recognizing Arguing Subjectivity and Argument Tags0
SAMAR: A System for Subjectivity and Sentiment Analysis of Arabic Social Media0
POLITICAL-ADS: An annotated corpus for modeling event-level evaluativity0
Who Did What to Whom? A Contrastive Study of Syntacto-Semantic Dependencies0
Sentiment Analysis Using a Novel Human Computation Game0
How do Negation and Modality Impact on Opinions?0
Multimodal Sentiment Analysis0
Mining Sentiments from Tweets0
Cross-discourse Development of Supervised Sentiment Analysis in the Clinical Domain0
Multilingual Sentiment Analysis using Machine Translation?0
Detection of Implicit Citations for Sentiment Detection0
How to Evaluate Opinionated Keyphrase Extraction?0
Semantic frames as an anchor representation for sentiment analysis0
Random Walk Weighting over SentiWordNet for Sentiment Polarity Detection on Twitter0
Analysis of Travel Review Data from Reader's Point of View0
Subjectivity Word Sense Disambiguation0
Multi-Domain Learning: When Do Domains Matter?0
Why Question Answering using Sentiment Analysis and Word Classes0
Do Neighbours Help? An Exploration of Graph-based Algorithms for Cross-domain Sentiment Classification0
Active Learning for Imbalanced Sentiment Classification0
Collocation Polarity Disambiguation Using Web-based Pseudo Contexts0
Automatically Constructing a Normalisation Dictionary for Microblogs0
UWashington: Negation Resolution using Machine Learning MethodsCode0
FBK: Exploiting Phrasal and Contextual Clues for Negation Scope Detection0
UMichigan: A Conditional Random Field Model for Resolving the Scope of Negation0
*SEM 2012 Shared Task: Resolving the Scope and Focus of Negation0
UCM-I: A Rule-based Syntactic Approach for Resolving the Scope of Negation0
Multilingual WSD with Just a Few Lines of Code: the BabelNet API0
QuickView: NLP-based Tweet Search0
Active Learning with Transfer Learning0
Graph-based Semi-Supervised Learning Algorithms for NLP0
Multilingual Subjectivity and Sentiment Analysis0
Identifying High-Impact Sub-Structures for Convolution Kernels in Document-level Sentiment Classification0
Show:102550
← PrevPage 111 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