Deep Convolution Neural Networks for Twitter Sentiment Analysis
Twitter sentiment analysis technology provides the methods to survey public emotion about the events or products related to them. Most of the current researches are focusing on obtaining sentiment features by analyzing lexical and syntactic features. These features are expressed explicitly through s...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8244338/ |
id |
doaj-c696a5e9620b483a8c5783888b2e963c |
---|---|
record_format |
Article |
spelling |
doaj-c696a5e9620b483a8c5783888b2e963c2021-03-29T20:53:19ZengIEEEIEEE Access2169-35362018-01-016232532326010.1109/ACCESS.2017.27769308244338Deep Convolution Neural Networks for Twitter Sentiment AnalysisZhao Jianqiang0https://orcid.org/0000-0003-0754-5292Gui Xiaolin1Zhang Xuejun2School of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, ChinaSchool of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, ChinaKey Laboratory of Computer Network, Xi’an Jiaotong University, Xi’an, ChinaTwitter sentiment analysis technology provides the methods to survey public emotion about the events or products related to them. Most of the current researches are focusing on obtaining sentiment features by analyzing lexical and syntactic features. These features are expressed explicitly through sentiment words, emoticons, exclamation marks, and so on. In this paper, we introduce a word embeddings method obtained by unsupervised learning based on large twitter corpora, this method using latent contextual semantic relationships and co-occurrence statistical characteristics between words in tweets. These word embeddings are combined with n-grams features and word sentiment polarity score features to form a sentiment feature set of tweets. The feature set is integrated into a deep convolution neural network for training and predicting sentiment classification labels. We experimentally compare the performance of our model with the baseline model that is a word n-grams model on five Twitter data sets, the results indicate that our model performs better on the accuracy and F1-measure for twitter sentiment classification.https://ieeexplore.ieee.org/document/8244338/Twittersentiment analysisword embeddingsconvolution neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhao Jianqiang Gui Xiaolin Zhang Xuejun |
spellingShingle |
Zhao Jianqiang Gui Xiaolin Zhang Xuejun Deep Convolution Neural Networks for Twitter Sentiment Analysis IEEE Access sentiment analysis word embeddings convolution neural network |
author_facet |
Zhao Jianqiang Gui Xiaolin Zhang Xuejun |
author_sort |
Zhao Jianqiang |
title |
Deep Convolution Neural Networks for Twitter Sentiment Analysis |
title_short |
Deep Convolution Neural Networks for Twitter Sentiment Analysis |
title_full |
Deep Convolution Neural Networks for Twitter Sentiment Analysis |
title_fullStr |
Deep Convolution Neural Networks for Twitter Sentiment Analysis |
title_full_unstemmed |
Deep Convolution Neural Networks for Twitter Sentiment Analysis |
title_sort |
deep convolution neural networks for twitter sentiment analysis |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
Twitter sentiment analysis technology provides the methods to survey public emotion about the events or products related to them. Most of the current researches are focusing on obtaining sentiment features by analyzing lexical and syntactic features. These features are expressed explicitly through sentiment words, emoticons, exclamation marks, and so on. In this paper, we introduce a word embeddings method obtained by unsupervised learning based on large twitter corpora, this method using latent contextual semantic relationships and co-occurrence statistical characteristics between words in tweets. These word embeddings are combined with n-grams features and word sentiment polarity score features to form a sentiment feature set of tweets. The feature set is integrated into a deep convolution neural network for training and predicting sentiment classification labels. We experimentally compare the performance of our model with the baseline model that is a word n-grams model on five Twitter data sets, the results indicate that our model performs better on the accuracy and F1-measure for twitter sentiment classification. |
topic |
Twitter sentiment analysis word embeddings convolution neural network |
url |
https://ieeexplore.ieee.org/document/8244338/ |
work_keys_str_mv |
AT zhaojianqiang deepconvolutionneuralnetworksfortwittersentimentanalysis AT guixiaolin deepconvolutionneuralnetworksfortwittersentimentanalysis AT zhangxuejun deepconvolutionneuralnetworksfortwittersentimentanalysis |
_version_ |
1724193982438703104 |