A Deep Neural Architecture for Sentence-level Sentiment Classification
in Twitter Social Networking
H. Nguyen, and M. Nguyen. (2017)cite arxiv:1706.08032Comment: PACLING Conference 2017, 6 pages.
Abstract
This paper introduces a novel deep learning framework including a
lexicon-based approach for sentence-level prediction of sentiment label
distribution. We propose to first apply semantic rules and then use a Deep
Convolutional Neural Network (DeepCNN) for character-level embeddings in order
to increase information for word-level embedding. After that, a Bidirectional
Long Short-Term Memory Network (Bi-LSTM) produces a sentence-wide feature
representation from the word-level embedding. We evaluate our approach on three
Twitter sentiment classification datasets. Experimental results show that our
model can improve the classification accuracy of sentence-level sentiment
analysis in Twitter social networking.
%0 Generic
%1 nguyen2017neural
%A Nguyen, Huy
%A Nguyen, Minh-Le
%D 2017
%K character cnn deep_learning rnn sentiment twitter
%T A Deep Neural Architecture for Sentence-level Sentiment Classification
in Twitter Social Networking
%U http://arxiv.org/abs/1706.08032
%X This paper introduces a novel deep learning framework including a
lexicon-based approach for sentence-level prediction of sentiment label
distribution. We propose to first apply semantic rules and then use a Deep
Convolutional Neural Network (DeepCNN) for character-level embeddings in order
to increase information for word-level embedding. After that, a Bidirectional
Long Short-Term Memory Network (Bi-LSTM) produces a sentence-wide feature
representation from the word-level embedding. We evaluate our approach on three
Twitter sentiment classification datasets. Experimental results show that our
model can improve the classification accuracy of sentence-level sentiment
analysis in Twitter social networking.
@misc{nguyen2017neural,
abstract = {This paper introduces a novel deep learning framework including a
lexicon-based approach for sentence-level prediction of sentiment label
distribution. We propose to first apply semantic rules and then use a Deep
Convolutional Neural Network (DeepCNN) for character-level embeddings in order
to increase information for word-level embedding. After that, a Bidirectional
Long Short-Term Memory Network (Bi-LSTM) produces a sentence-wide feature
representation from the word-level embedding. We evaluate our approach on three
Twitter sentiment classification datasets. Experimental results show that our
model can improve the classification accuracy of sentence-level sentiment
analysis in Twitter social networking.},
added-at = {2018-02-28T20:42:14.000+0100},
author = {Nguyen, Huy and Nguyen, Minh-Le},
biburl = {https://www.bibsonomy.org/bibtex/23ee3b1ceeff2c95a0d73a97f0e706af5/dallmann},
description = {1706.08032.pdf},
interhash = {3dc6979487ea0e2972fa1ceaabd9c212},
intrahash = {3ee3b1ceeff2c95a0d73a97f0e706af5},
keywords = {character cnn deep_learning rnn sentiment twitter},
note = {cite arxiv:1706.08032Comment: PACLING Conference 2017, 6 pages},
timestamp = {2018-02-28T20:42:14.000+0100},
title = {A Deep Neural Architecture for Sentence-level Sentiment Classification
in Twitter Social Networking},
url = {http://arxiv.org/abs/1706.08032},
year = 2017
}