Corpus ID: 15874232

Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts

@inproceedings{Santos2014DeepCN,
  title={Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts},
  author={C. D. Santos and M. Gatti},
  booktitle={COLING},
  year={2014}
}
Sentiment analysis of short texts such as single sentences and Twitter messages is challenging because of the limited contextual information that they normally contain. [...] Key Method We apply our approach for two corpora of two different domains: the Stanford Sentiment Treebank (SSTb), which contains sentences from movie reviews; and the Stanford Twitter Sentiment corpus (STS), which contains Twitter messages. For the SSTb corpus, our approach achieves state-of-the-art results for single sentence sentiment…Expand
Deep Convolution Neural Networks for Twitter Sentiment Analysis
TLDR
A word embeddings method obtained by unsupervised learning based on large twitter corpora is introduced, this method using latent contextual semantic relationships and co-occurrence statistical characteristics between words in tweets to form a sentiment feature set of tweets. Expand
Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts
TLDR
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. Expand
Gated Neural Networks for Targeted Sentiment Analysis
TLDR
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. Expand
DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS
TLDR
A deep neural network model that uses bilingual word embeddings to effectively solve sentiment classification problem for a given pair of languages, applies to two corpora of two different language pairs: English-Russian and Russian-Kazakh. Expand
Deep Learning Based Sentiment Analysis on Product Reviews on Twitter
TLDR
This paper presents a deep learning based scheme for sentiment analysis on Twitter messages, and the prediction results obtained by deep-learning based schemes have been compared to conventional classifiers. Expand
Twitter Sentiment Analysis using Distributed Word and Sentence Representation
TLDR
This paper classifies tweets into positive and negative sentiments, but instead of using traditional methods or preprocessing text data here they use the distributed representations of words and sentences to classify the tweets. Expand
Sentiment strength detection with a context-dependent lexicon-based convolutional neural network
TLDR
Experimental results indicate that the proposed model can predict the sentiment strength of documents more effectively than the baseline methods, and that the SSS-Lex is of higher quality than the existing lexicons. Expand
Sentence Modeling with Deep Neural Architecture using Lexicon and Character Attention Mechanism for Sentiment Classification
TLDR
Experimental results show that the novel approach to sentiment analysis that uses lexicon features for building lexicon embeddings and generates character attention vectors by using a Deep Convolutional Neural Network can improve the classification accuracy of sentence-level sentiment analysis in Twitter social networking. Expand
Leveraging multiple features for document sentiment classification
TLDR
Experimental results on open datasets demonstrate that the proposed novel text sentiment classification method could effectively improve the sentiment classification performance compared with the basic models and state-of-the-art methods. Expand
Three Convolutional Neural Network-based models for learning Sentiment Word Vectors towards sentiment analysis
TLDR
Three Convolutional Neural Network (CNN)-based models to learn sentiment word vectors (SWV), which integrate sentiment information with semantic and syntactic information into word representations in three different strategies are presented. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 21 REFERENCES
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
TLDR
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. Expand
Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
TLDR
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. Expand
SemEval-2013 Task 2: Sentiment Analysis in Twitter
TLDR
Crowdourcing on Amazon Mechanical Turk was used to label a large Twitter training dataset along with additional test sets of Twitter and SMS messages for both subtasks, which included two subtasks: A, an expression-level subtask, and B, a message level subtask. Expand
Learning Character-level Representations for Part-of-Speech Tagging
TLDR
A deep neural network is proposed that learns character-level representation of words and associate them with usual word representations to perform POS tagging and produces state-of-the-art POS taggers for two languages. Expand
Semantic Compositionality through Recursive Matrix-Vector Spaces
TLDR
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. Expand
Text segmentation with character-level text embeddings
TLDR
This work proposes to learn text representations directly from raw character sequences by training a Simple Recurrent Network to predict the next character in text and uses the learned text embeddings as features in a supervised character level text segmentation and labeling task. Expand
Twitter Polarity Classification with Label Propagation over Lexical Links and the Follower Graph
TLDR
Results on polarity classification for several datasets show that the label propagation approach rivals a model supervised with in-domain annotated tweets, and it outperforms the noisily supervised classifier it exploits as well as a lexicon-based polarity ratio classifier. Expand
Robust Sentiment Detection on Twitter from Biased and Noisy Data
In this paper, we propose an approach to automatically detect sentiments on Twitter messages (tweets) that explores some characteristics of how tweets are written and meta-information of the wordsExpand
Deep Learning for Chinese Word Segmentation and POS Tagging
TLDR
This study explores the feasibility of performing Chinese word segmentation and POS tagging by deep learning, and describes a perceptron-style algorithm for training the neural networks, as an alternative to maximum-likelihood method to speed up the training process and make the learning algorithm easier to be implemented. Expand
Better Word Representations with Recursive Neural Networks for Morphology
TLDR
This paper combines recursive neural networks, where each morpheme is a basic unit, with neural language models to consider contextual information in learning morphologicallyaware word representations and proposes a novel model capable of building representations for morphologically complex words from their morphemes. Expand
...
1
2
3
...