Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts

By C. D. Santos, Maíra Athanázio de Cerqueira Gatti. 2014

1,327 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Character-level Convolutional Networks for Text Classification (2015, background): “It has been shown that ConvNets can be directly applied to distributed [6] [16] or discrete [13] embedding of words, without any knowledge on the syntactic or semantic structures of a language.”
Enriching Word Vectors with Subword Information (2016, background): “Recently, several works have proposed different composition functions to derive representations of words from morphemes (Lazaridou et al., 2013; Luong et al., 2013; Botha and Blunsom, 2014; Qiu et al., 2014).”
Learning Gender-Neutral Word Embeddings (2018, background): “Word Embeddings Word embeddings serve as a fundamental building block for a broad range of NLP applications (dos Santos and Gatti, 2014; Bahdanau et al., 2014; Zeng et al., 2015) and various approaches (Mikolov et al., 2013b; Pen-nington et al., 2014; Levy et al., 2015) have been proposed for…”
SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “Previous work [6, 11, 15] mainly focuses on sentiment classification based on the concrete content posted by users.”
Recent Trends in Deep Learning Based Natural Language Processing (2017, background): “Generally speaking, building natural language understanding systems at the character level has attracted certain research attention [28, 29, 30, 31].”
Representation learning for very short texts using weighted word embedding aggregation (2016, methodology): “…embeddings through a mean, max, min... function is still one of the most easy and widely used techniques to derive sentence embeddings, often in combination with an MLP or convolutional network (Weston et al. (2014); dos Santos and Gatti (2014); Yin and Sch¨utze (2015); Collobert et al. (2011)).”
Very Deep Convolutional Networks for Natural Language Processing (2016, methodology): “The use of character level information was also proposed by dos Santos and Gatti [5]: all the character embeddings of one word are combined by a max operation and they are then jointly used with the word embedding information.”
A Primer on Neural Network Models for Natural Language Processing (2015, background): “…with a handful of small matrices needs to be stored), and being able to provide an embedding vector for every word that may be encountered. dos Santos and Gatti (2014) and dos Santos and Zadrozny (2014) model the embedding of a word using a convolutional network (see Section 9) over the…”
When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data (2017, methodology): “State-of-the-art sentiment analyzers use deep learning techniques like Convolutional Neural Network (CNN) (Dos Santos and Gatti, 2014) and Recursive Neural Network (Tang et al., 2015) based approach to learn features automatically from the input text.”
A Survey of the Usages of Deep Learning for Natural Language Processing (2020, neutral): “CNNs are used extensively in image and video processing, as well as speech and NLP [20], [21], [22], [23].”
Gated Neural Networks for Targeted Sentiment Analysis (2016, methodology): “…Tang et al. 2014; Vo and Zhang 2015) and deep neural network structures (Irsoy and Cardie 2013; Paulus, Socher, and Manning 2014; Kalchbrenner, Grefenstette, and Blunsom 2014; Zhou et al. 2014; Dong et al. 2014; dos Santos and Gatti 2014) have been used for the task, giving competitive accuracies.”
Incorporating Relation Paths in Neural Relation Extraction (2016, methodology): “We integrate the information from both direct sentences and relation paths, then predict the confidence of each relation.”
Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts (2016, methodology): “Convolution is widely used in sentence modeling (Kim, 2014; Kalchbrenner et al., 2014; dos Santos and Gatti, 2014).”
Multi-document Summarization via Deep Learning Techniques: A Survey (2020, background): “ng operation on features at intervals can get different levels of features from simple to complex. Convolutional neural networks have been proved to be effective for various NLP tasks in recent years [31, 58]. They are able to process natural language after sentences/words vectorization. Most of the”