Deep learning for sentiment analysis: A survey
Wiley Interdisciplinary Reviews Data Mining and Knowledge DiscoveryPublished 30 March 2018Open access
Lei Zhang, Shuai Wang, Bing Liu
Citations1,868
SJR quartileQ1
SJR score2.20
SNIP4.05
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An overview of deep learning is given and a comprehensive survey of its current applications in sentiment analysis is provided.
Abstract
Deep learning has emerged as a powerful machine learning technique that learns multiple layers of representations or features of the data and produces state‐of‐the‐art prediction results. Along with the success of deep learning in many application domains, deep learning is also used in sentiment analysis in recent years. This paper gives an overview of deep learning and then provides a comprehensive survey of its current applications in sentiment analysis. This article is categorized under: Fundamental Concepts of Data and Knowledge > Data Concepts Algorithmic Development > Text Mining
Keywords
Computer Science
Neural ComputationLong Short-Term Memory
98,079 Citations1997Sepp Hochreiter, Jürgen Schmidhuber
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Glove: Global Vectors for Word Representation
33,769 Citations2014Jeffrey Pennington, Richard Socher +1 more
A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
24,447 Citations2014Kyunghyun Cho, Bart van Merriënboer +5 more
Qualitatively, the proposed RNN Encoder‐Decoder model learns a semantically and syntactically meaningful representation of linguistic phrases.
ScienceReducing the Dimensionality of Data with Neural Networks
20,953 Citations2006Geoffrey E. Hinton, Ruslan Salakhutdinov
arXiv (Cornell University)Distributed Representations of Words and Phrases and their Compositionality
18,086 Citations2013Tomáš Mikolov, Ilya Sutskever +3 more
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
18,050 Citations2013Tomáš Mikolov, Kai Chen +2 more
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
Convolutional Neural Networks for Sentence Classification
13,798 Citations2014Yoon Kim
The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRepresentation Learning: A Review and New Perspectives
13,002 Citations2013Yoshua Bengio, Aaron Courville +1 more
Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
11,710 Citations2013Tomáš Mikolov, Kai Chen +2 more
Cognitive ScienceFinding Structure in Time
10,841 Citations1990Jeffrey L. Elman
A proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory and suggests a method for representing lexical categories and the type/token distinction is developed.
IEEE Transactions on Signal ProcessingBidirectional recurrent neural networks
10,022 Citations1997Mike Schuster, Kuldip K. Paliwal
It is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution.
IEEE Transactions on Neural NetworksLearning long-term dependencies with gradient descent is difficult
8,461 Citations1994Yoshua Bengio, P. Simard +1 more
This work shows why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases, and exposes a trade-off between efficient learning by gradient descent and latching on information for long periods.
Extracting and composing robust features with denoising autoencoders
7,343 Citations2008Pascal Vincent, Hugo Larochelle +2 more
This work introduces and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern.
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
6,774 Citations2013Richard Socher, Alex Perelygin +5 more
A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network.
Foundations and Trends® in Information RetrievalOpinion Mining and Sentiment Analysis
6,204 Citations2008Bo Pang, Lillian Lee
This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems and focuses on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis.
Neural NetworksFramewise phoneme classification with bidirectional LSTM and other neural network architectures
5,463 Citations2005Alex Graves, Jürgen Schmidhuber
The main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs).
Deep Sparse Rectifier Neural Networks
5,408 Citations2012Xavier Glorot, Antoine Bordes +1 more
This paper shows that rectifying neurons are an even better model of biological neurons and yield equal or better performance than hyperbolic tangent networks in spite of the hard non-linearity and non-dierentiabil ity.
arXiv (Cornell University)Distributed Representations of Sentences and Documents
5,128 Citations2014Quoc V. Le, Tomáš Mikolov
Paragraph Vector is an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents, and its construction gives the algorithm the potential to overcome the weaknesses of bag-of-words models.
Hierarchical Attention Networks for Document Classification
4,829 Citations2016Zichao Yang, Diyi Yang +4 more
Experiments conducted on six large scale text classification tasks demonstrate that the proposed architecture outperform previous methods by a substantial margin.
The MIT Press eBooksGreedy Layer-Wise Training of Deep Networks
4,704 Citations2007Yoshua Bengio, Pascal Lamblin +2 more
These experiments confirm the hypothesis that the greedy layer-wise unsupervised training strategy mostly helps the optimization, by initializing weights in a region near a good local minimum, giving rise to internal distributed representations that are high-level abstractions of the input, bringing better generalization.
Natural Language Processing (almost) from Scratch
3,987 Citations2011Ronan Collobert, Jason Weston +4 more
A Convolutional Neural Network for Modelling Sentences
3,561 Citations2014Nal Kalchbrenner, Edward Grefenstette +1 more
A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.
Learning Word Vectors for Sentiment Analysis
3,299 Citations2011Andrew L. Maas, Raymond E. Daly +4 more
This work presents a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term--document information as well as rich sentiment content, and finds it out-performs several previously introduced methods for sentiment classification.
Journal of Machine Learning ResearchA neural probabilistic language model
2,663 Citations2003BengioYoshua, DucharmeRéjean +2 more
This work reports on experiments using neural networks for the probability function, showing on two text corpora that the proposed approach very significantly improves on a state-of-the-art trigram model.
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
2,446 Citations2009Honglak Lee, Roger Grosse +2 more
The convolutional deep belief network is presented, a hierarchical generative model which scales to realistic image sizes and is translation-invariant and supports efficient bottom-up and top-down probabilistic inference.
Attention-based LSTM for Aspect-level Sentiment Classification
2,344 Citations2016Yequan Wang, Minlie Huang +2 more
This paper reveals that the sentiment polarity of a sentence is not only determined by the content but is also highly related to the concerned aspect, and proposes an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification.
Synthesis lectures on human language technologiesSentiment Analysis and Opinion Mining
1,761 Citations2012Bing Liu
Document Modeling with Gated Recurrent Neural Network for Sentiment Classification
1,535 Citations2015Duyu Tang, Bing Qin +1 more
A neural network model is introduced to learn vector-based document representation in a unified, bottom-up fashion and dramatically outperforms standard recurrent neural network in document modeling for sentiment classification.
Semantic Compositionality through Recursive Matrix-Vector Spaces
1,297 Citations2012Richard Socher, Brody Huval +2 more
A recursive neural network model that learns compositional vector representations for phrases and sentences of arbitrary syntactic type and length and can learn the meaning of operators in propositional logic and natural language is introduced.
Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
1,198 Citations2011Richard Socher, Jeffrey Pennington +3 more
A novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions that outperform other state-of-the-art approaches on commonly used datasets, without using any pre-defined sentiment lexica or polarity shifting rules.
International Conference on Computational LinguisticsDeep Convolutional Neural Networks for Sentiment Analysis of Short Texts
1,191 Citations2014Cícero dos Santos, Maíra Gatti de Bayser
A new deep convolutional neural network is proposed that exploits from characterto sentence-level information to perform sentiment analysis of short texts and achieves state-of-the-art results for single sentence sentiment prediction.
Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
1,167 Citations2014Duyu Tang, Furu Wei +4 more
Three neural networks are developed to effectively incorporate the supervision from sentiment polarity of text (e.g. sentences or tweets) in their loss functions and the performance of SSWE is improved by concatenating SSWE with existing feature set.
Improving Word Representations via Global Context and Multiple Word Prototypes
1,101 Citations2012Eric Huang, Richard Socher +2 more
A new neural network architecture is presented which learns word embeddings that better capture the semantics of words by incorporating both local and global document context, and accounts for homonymy and polysemy by learning multiple embedDings per word.
Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification
1,066 Citations2014Li Dong, Furu Wei +4 more
AdaRNN adaptively propagates the sentiments of words to target depending on the context and syntactic relationships between them and it is shown that AdaRNN improves the baseline methods.
Aspect Level Sentiment Classification with Deep Memory Network
1,035 Citations2016Duyu Tang, Bing Qin +1 more
A deep memory network for aspect level sentiment classification that explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect, and is also fast.
Recurrent Attention Network on Memory for Aspect Sentiment Analysis
1,024 Citations2017Peng Chen, Zhongqian Sun +2 more
A novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review that adopts multiple-attention mechanism to capture sentiment features separated by a long distance, so that it is more robust against irrelevant information.
Interactive Attention Networks for Aspect-Level Sentiment Classification
1,014 Citations2017Dehong Ma, Sujian Li +2 more
It is argued that both targets and contexts deserve special treatment and need to be learned their own representations via interactive learning and proposed the interactive attention networks (IAN) to interactively learn attentions in the contexts and targets.
Knowledge-Based SystemsAspect extraction for opinion mining with a deep convolutional neural network
852 Citations2016Soujanya Poria, Erik Cambria +1 more
This paper used a 7-layer deep convolutional neural network to tag each word in opinionated sentences as either aspect or non-aspect word, and developed a set of linguistic patterns for the same purpose and combined them with the neural network.
International Conference on Artificial Intelligence and StatisticsHierarchical Probabilistic Neural Network Language Model.
840 Citations2005Fréderic Morin, Yoshua Bengio
A point-of-care POC analyzer that can rapidly measure both medications used for treatment and illicit drugs in patient saliva and shows evidence of accuracy in measuring treatment medications and relapse to drug use is shown.
Context-Dependent Sentiment Analysis in User-Generated Videos
839 Citations2017Soujanya Poria, Erik Cambria +4 more
A LSTM-based model is proposed that enables utterances to capture contextual information from their surroundings in the same video, thus aiding the classification process and showing 5-10% performance improvement over the state of the art and high robustness to generalizability.
Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
776 Citations2015Rie Johnson, Tong Zhang
A straightforward adaptation of CNN from image to text, a simple but new variation which employs bag-of-word conversion in the convolution layer is proposed and an extension to combine multiple convolution layers is explored for higher accuracy.
Proceedings of the AAAI Conference on Artificial IntelligenceEmotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
749 Citations2018Hao Zhou, Minlie Huang +3 more
This paper proposes Emotional Chatting Machine (ECM), the first work that addresses the emotion factor in large-scale conversation generation using three new mechanisms that respectively models the high-level abstraction of emotion expressions by embedding emotion categories.
Traffic sign recognition with multi-scale Convolutional Networks
747 Citations2011Pierre Sermanet, Yann LeCun
This work applies Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition, and yields the 2nd-best accuracy above the human performance.
Expert Systems with ApplicationsDocument-level sentiment classification: An empirical comparison between SVM and ANN
724 Citations2012Rodrigo Moraes, João Francisco Valiati +1 more
An empirical comparison between SVM and ANN regarding document-level sentiment analysis is presented and it is indicated that ANN produce superior or at least comparable results to SVM's, even on the context of unbalanced data.
Dimensional Sentiment Analysis Using a Regional CNN-LSTM Model
587 Citations2016Jin Wang, Liang Yu +2 more
A regional CNN-LSTM model consisting of two parts: regional CNN and LSTM to predict the VA ratings of texts is proposed, showing that the proposed method outperforms lexicon-based, regression- based, and NN-based methods proposed in previous studies.
arXiv (Cornell University)Effective LSTMs for Target-Dependent Sentiment Classification
559 Citations2015Duyu Tang, Bing Qin +2 more
Deep Convolutional Neural Network Textual Features and Multiple Kernel Learning for Utterance-level Multimodal Sentiment Analysis
534 Citations2015Soujanya Poria, Erik Cambria +1 more
A novel way of extracting features from short texts, based on the activation values of an inner layer of a deep convolutional neural network, is presented and a parallelizable decision-level data fusion method is presented, which is much faster, though slightly less accurate.
Development and use of a gold-standard data set for subjectivity classifications
498 Citations1999Janyce Wiebe, Rebecca Bruce +1 more
Bias-corrected tags are formulated and successfully used to guide a revision of the coding manual and develop an automatic classifier.
Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings
497 Citations2015Pengfei Liu, Shafiq Joty +1 more
This work proposes a general class of discriminative models based on recurrent neural networks and word embeddings that can be successfully applied to fine-grained opinion mining tasks without any taskspecific feature engineering effort.
Proceedings of the AAAI Conference on Artificial IntelligenceCoupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms
440 Citations2017Wenya Wang, Sinno Jialin Pan +2 more
A novel deep learning model, named coupled multi-layer attentions, where each layer consists of a couple of attentions with tensor operators that are learned interactively to dually propagate information between aspect terms and opinion terms.
Neural Information Processing SystemsLearning word embeddings efficiently with noise-contrastive estimation
438 Citations2013Andriy Mnih, Koray Kavukcuoglu
This work proposes a simple and scalable new approach to learning word embeddings based on training log-bilinear models with noise-contrastive estimation, and achieves results comparable to the best ones reported, using four times less data and more than an order of magnitude less computing time.
An Unsupervised Neural Attention Model for Aspect Extraction
428 Citations2017Ruidan He, Wee Sun Lee +2 more
A novel neural approach that improves coherence by exploiting the distribution of word co-occurrences through the use of neural word embeddings, and uses an attention mechanism to de-emphasize irrelevant words during training, further improving the coherence of aspects.
Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis
422 Citations2016Wenya Wang, Sinno Jialin Pan +2 more
A novel joint model that integrates recursive neural networks and conditional random fields into a unified framework for explicit aspect and opinion terms co-extraction and is flexible to incorporate hand-crafted features into the proposed model to further boost its information extraction performance.
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm
408 Citations2017Bjarke Felbo, Alan Mislove +3 more
This paper shows that by extending the distant supervision to a more diverse set of noisy labels, the models can learn richer representations and obtain state-of-the-art performance on 8 benchmark datasets within emotion, sentiment and sarcasm detection using a single pretrained model.
Opinion Mining with Deep Recurrent Neural Networks
386 Citations2014Ozan İrsoy, Claire Cardie
This approach outperforms previous CRF-based baselines, including the state-of-the-art semi-Markov CRF model, and does so without access to the powerful opinion lexicons and syntactic features relied upon by the semi-CRF, as well as without the standard layer-by-layer pre-training typically required of RNN architectures.
Learning Semantic Representations of Users and Products for Document Level Sentiment Classification
379 Citations2015Duyu Tang, Bing Qin +1 more
By combining evidence at user-, product and documentlevel in a unified neural framework, the proposed model achieves state-of-the-art performances on IMDB and Yelp datasets1.
EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks
377 Citations2017Muhammad Abdul-Mageed, Lyle Ungar
A very large dataset for fine-grained emotions and deep learning models on it are built and a new state-of-the-art on 24 fine- grained types of emotions is achieved.
Neural Sentiment Classification with User and Product Attention
344 Citations2016Huimin Chen, Maosong Sun +3 more
A hierarchical neural network is proposed to incorporate global user and product information into sentiment clas-sification through at-tentions over different semantic levels due to its ability of capturing crucial semantic components.
IEEE Transactions on Knowledge and Data EngineeringSentiment Embeddings with Applications to Sentiment Analysis
335 Citations2015Duyu Tang, Furu Wei +4 more
This work develops a number of neural networks with tailoring loss functions, and applies sentiment embeddings to word-level sentiment analysis, sentence level sentiment classification, and building sentiment lexicons, showing results that consistently outperform context-basedembeddings on several benchmark datasets of these tasks.
Proceedings of the AAAI Conference on Artificial IntelligenceGated Neural Networks for Targeted Sentiment Analysis
313 Citations2016Meishan Zhang, Yue Zhang +1 more
A sentence-level neural model is proposed to address the limitation of pooling functions, which do not explicitly model tweet-level semantics and gives significantly higher accuracies compared to the current best method for targeted sentiment analysis.
International Conference on Artificial IntelligenceTarget-dependent twitter sentiment classification with rich automatic features
307 Citations2015Duy-Tin Vo, Yue Zhang
This paper shows that competitive results can be achieved without the use of syntax, by extracting a rich set of automatic features from a tweet, using distributed word representations and neural pooling functions to extract features.
Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory
297 Citations2015Xin Wang, Yuanchao Liu +3 more
Long ShortTerm Memory (LSTM) recurrent network for twitter sentiment prediction is introduced, with the help of gates and constant error carousels in the memory block structure, to handle interactions between words through a flexible compositional function.
International Conference on Computational LinguisticsCombination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts
273 Citations2016Xingyou Wang, Weijie Jiang +1 more
A jointed CNN and RNN architecture is described, taking advantage of the coarse-grained local features generated by CNN and long-distance dependencies learned via RNN for sentiment analysis of short texts.
Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction
260 Citations2017Xin Li, Wai Lam
A novel LSTM-based deep multi-task learning framework for aspect term extraction from user review sentences designed for jointly handling the extraction tasks of aspects and opinions via memory interactions is proposed.
neural information processing systemsDeep Recursive Neural Networks for Compositionality in Language
259 Citations2014Ozan İrsoy, Claire Cardie
The results show that deep RNNs outperform associated shallow counterparts that employ the same number of parameters and outperforms previous baselines on the sentiment analysis task, including a multiplicative RNN variant as well as the recently introduced paragraph vectors.
Attention Modeling for Targeted Sentiment
246 Citations2017Jiangming Liu, Yue Zhang
Results show that by using attention to model the contribution of each word in a sentence with respect to the target, this model gives significantly improved results over two standard benchmarks.
Neural Networks for Open Domain Targeted Sentiment
246 Citations2015Meishan Zhang, Yue Zhang +1 more
This work empirically studies the effect of word embeddings and automatic feature combinations on the open domain targeted sentiment task by extending a CRF baseline using neural networks, and proposes a novel integration of neural and discrete features which combines their relative advantages, leading to significantly higher results compared to both baselines.
Do Multi-Sense Embeddings Improve Natural Language Understanding?
242 Citations2015Jiwei Li, Dan Jurafsky
A multisense embedding model based on Chinese Restaurant Processes is introduced that achieves state of the art performance on matching human word similarity judgments, and a pipelined architecture for incorporating multi-sense embeddings into language understanding is proposed.
Learning Sentence Embeddings with Auxiliary Tasks for Cross-Domain Sentiment Classification
225 Citations2016Jianfei Yu, Jing Jiang
This paper borrows the idea from Structural Correspondence Learning and uses two auxiliary tasks to help induce a sentence embedding that supposedly works well across domains for sentiment classification and proposes to jointly learn this sentenceembedding together with the sentiment classI-class itself.
End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification
224 Citations2017Zheng Li, Yu Zhang +3 more
An end-to-end Adversarial Memory Network (AMN) is introduced for cross-domain sentiment classification that can automatically capture the pivots using an attention mechanism and can significantly outperform state-of-the-art methods.
Proceedings of the AAAI Conference on Artificial IntelligenceUsing Deep and Convolutional Neural Networks for Accurate Emotion Classification on DEAP Data
220 Citations2017Samarth Tripathi, Shrinivas Acharya +3 more
This research is a testament that Neural Networks could be robust classifiers for brain signals, even outperforming traditional learning techniques.
Proceedings of the AAAI Conference on Artificial IntelligenceAttention Based LSTM for Target Dependent Sentiment Classification
209 Citations2017Min Yang, Wenting Tu +3 more
An attention-based bidirectional LSTM approach to improve the target-dependent sentiment classification by learning the alignment between the target entities and the most distinguishing features.
arXiv (Cornell University)A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks
204 Citations2016Soujanya Poria, Erik Cambria +2 more
Select-additive learning: Improving generalization in multimodal sentiment analysis
203 Citations2017Haohan Wang, Aaksha Meghawat +2 more
This paper proposes a Select-Additive Learning (SAL) procedure that improves the generalizability of trained neural networks for multimodal sentiment analysis and shows that this approach improves prediction accuracy significantly in all three modalities (verbal, acoustic, visual), as well as in their fusion.
Using Deep and Convolutional Neural Networks for Accurate Emotion Classification on DEAP Dataset.
198 Citations2017Samarth Tripathi, Shrinivas Acharya +3 more
Joint Inference for Fine-grained Opinion Extraction
198 Citations2013Bishan Yang, Claire Cardie
Experimental results demonstrate that the joint inference approach significantly outperforms traditional pipeline methods and baselines that tackle subtasks in isolation for the problem of opinion extraction.
Refining Word Embeddings for Sentiment Analysis
190 Citations2017Liang-Chih Yu, Jin Wang +2 more
The proposed word vector refinement model is based on adjusting the vector representations of words such that they can be closer to both semantically and sentimentally similar words and further away from sentimentally dissimilar words.
A Question Answering Approach for Emotion Cause Extraction
187 Citations2017Lin Gui, Jiannan Hu +4 more
A new approach is proposed which considers emotion cause identification as a reading comprehension task in QA, and a new mechanism to store relevant context in different memory slots to model context information is proposed.
Cached Long Short-Term Memory Neural Networks for Document-Level Sentiment Classification
186 Citations2016Jiacheng Xu, Danlu Chen +2 more
A Cached Long Short-Term Memory neural networks (CLSTM) to capture the overall semantic information in long texts and introduces a cache mechanism, which divides memory into several groups with different forgetting rates and thus enables the network to keep sentiment information better within a recurrent unit.
Context-Sensitive Lexicon Features for Neural Sentiment Analysis
180 Citations2016Zhiyang Teng, Duy Tin Vo +1 more
This work proposes a context-sensitive lexicon-based method based on a simple weighted-sum model, using a recurrent neural network to learn the sen-timents strength, intensification and negation of lexicon sentiments in composing the sentiment value of sentences.
Linguistically Regularized LSTM for Sentiment Classification
174 Citations2017Qian Qiao, Minlie Huang +2 more
Results show that the proposed simple models are able to capture the linguistic role of sentiment words, negation words, and intensity words in sentiment expression.
Are Word Embedding-based Features Useful for Sarcasm Detection?
171 Citations2016Aditya Joshi, Vaibhav Tripathi +3 more
A comparison of the four embeddings shows that Word2Vec and dependency weight-based features outperform LSA and GloVe, in terms of their benefit to sarcasm detection.
Proceedings of the AAAI Conference on Artificial IntelligenceVisual Sentiment Analysis by Attending on Local Image Regions
167 Citations2017Quanzeng You, Hailin Jin +1 more
The proposed model utilizes the recent studied attention mechanism to jointly discover the relevant local regions and build a sentiment classifier on top of these local regions, capable of automatically discovering sentimental local regions of given images and outperforms existing state-of-the-art algorithms to visual sentiment analysis.
Proceedings of the AAAI Conference on Artificial IntelligenceLearning Visual Sentiment Distributions via Augmented Conditional Probability Neural Network
164 Citations2017Jufeng Yang, Ming Sun +1 more
Two new algorithms are developed based on conditional probability neural network (CPNN) which encodes image label into a binary representation to replace the signless integers used in CPNN, and employ it as a part of input for the neural network.
International Conference on Computational LinguisticsA Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks
162 Citations2016Soujanya Poria, Erik Cambria +2 more
This work develops models based on a pre-trained convolutional neural network for extracting sentiment, emotion and personality features for sarcasm detection and addresses the often ignored generalizability issue of classifying data that have not been seen by the models at learning phase.
International Conference on Computational LinguisticsWord Embeddings and Convolutional Neural Network for Arabic Sentiment Classification
155 Citations2016Abdelghani Dahou, Shengwu Xiong +3 more
A scheme of Arabic sentiment classification, which evaluates and detects the sentiment polarity from Arabic reviews and Arabic social media, is studied and it is shown that the proposed scheme outperforms the existed methods on 4 out of 5 balanced and unbalanced datasets.
International Conference on Computational LinguisticsTweet Sarcasm Detection Using Deep Neural Network
154 Citations2016Meishan Zhang, Yue Zhang +1 more
This work investigates the use of neural network for tweet sarcasm detection, and compares the effects of the continuous automatic features with discrete manual features.
Sentiment classification based on supervised latent n-gram analysis
153 Citations2011Dmitriy Bespalov, Bing Bai +2 more
A deep neural network is utilized to build a unified discriminative framework that allows for estimating the parameters of the latent space as well as the classification function with a bias for the target classification task at hand.
Magnets for Sarcasm: Making Sarcasm Detection Timely, Contextual and Very Personal
152 Citations2017Aniruddha Ghosh, Tony Veale
Using a neural architecture, it is shown that the mood exhibited by a speaker over tweets leading up to a new post is as useful a cue for sarcasm as the topical context of the post itself.
Stance Classification with Target-specific Neural Attention
152 Citations2017Jiachen Du, Ruifeng Xu +2 more
A neural network-based model is proposed, which incorporates target-specific information into stance classification by following a novel attention mechanism, which achieves the state-of-the-art performance of stance detection.
Investigating LSTMs for Joint Extraction of Opinion Entities and Relations
144 Citations2016Arzoo Katiyar, Claire Cardie
It is found that standard LSTMs are not competitive with a state-of-the-art CRF+ILP joint inference approach to opinion entities extraction, performing below even the standalone sequence-tagging CRF.
Extracting Opinion Expressions with semi-Markov Conditional Random Fields
140 Citations2012Bishan Yang, Claire Cardie
This work extends the original semi-CRF model to allow the modeling of arbitrarily long expressions while accounting for their likely syntactic structure when modeling segment boundaries, and demonstrates that this approach outperforms state-of-the-art methods for both opinion expression tasks.
Dependency Exploitation: A Unified CNN-RNN Approach for Visual Emotion Recognition
135 Citations2017Xinge Zhu, Liang Li +5 more
This paper proposes a unified CNNRNN model to predict the emotion based on the fused features from different levels by exploiting the dependency among them and leverages convolutional neural network with multiple layers to extract different levels of features within a multi-task learning framework.
International Conference on Computational LinguisticsA Hybrid Deep Learning Architecture for Sentiment Analysis
130 Citations2016Shad Akhtar, Ayush Kumar +2 more
A novel hybrid deep learning archtecture which is highly efficient for sentiment analysis in resource-poor languages such as Hindi and often outperforms the state-of-art systems is proposed.
Real-Time Speech Emotion and Sentiment Recognition for Interactive Dialogue Systems
127 Citations2016Dario Bertero, Farhad Bin Siddique +4 more
A CNN model is described to extract emotion from raw speech input without feature engineering and achieves an impressive average of 65.7% accuracy on six emotion categories, a 4.5% improvement when compared to the conventional feature based SVM classification.
ACM Transactions on Information SystemsEncoding Syntactic Knowledge in Neural Networks for Sentiment Classification
121 Citations2017Minlie Huang, Qian Qiao +1 more
This article proposes to learn tag-specific composition functions and tag embeddings in recursive neural networks, and proposes to utilize POS tags to control the gates of tree-structured LSTM networks.
Proceedings of the AAAI Conference on Artificial IntelligenceRecurrent Neural Networks with Auxiliary Labels for Cross-Domain Opinion Target Extraction
120 Citations2017Ying Ding, Jianfei Yu +1 more
This work uses rule-based unsupervised methods to create auxiliary labels and use neural network models to learn a hidden representation that works well for different domains and finds that it can outperform a number of strong baselines with a large margin.
Dyadic Memory Networks for Aspect-based Sentiment Analysis
119 Citations2017Yi Tay, Luu Anh Tuan +1 more
This paper proposes Dyadic Memory Networks (DyMemNN), a novel extension of end-to-end memory networks for aspect-based sentiment analysis (ABSA) that achieves the state-of-the-art performance and outperform many neural architectures across six benchmark datasets.
…