Study of Sentiment Classification for Chinese Microblog Based on Recurrent Neural Network

Zhang, Yangsen; Jiang, Yuru; Tong, Yixuan

doi:10.1049/cje.2016.07.002

Cited by 42 publications

(17 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Very recently, distributed representation starts attracting researchers' attention due to its capability in learning robust features [11,12] . Since the superior performance of deep learning, researchers began to use deep neural networks to learn distributed and robust feature representation of texts for sentiment classification [13][14][15][16] .…”

Section: Single Modality Sentiment Analysismentioning

confidence: 99%

Multi‐level Deep Correlative Networks for Multi‐modal Sentiment Analysis

et al. 2020

View full text Add to dashboard Cite

Section: Single Modality Sentiment Analysismentioning

confidence: 99%

Multi‐level Deep Correlative Networks for Multi‐modal Sentiment Analysis

et al. 2020

View full text Add to dashboard Cite

“…To improve the study of affective computing in social networks, some standard corpus based on weibo data had been published [ 45 – 47 ]. Inspired by the excellent performance of deep neural network in image recognition, a lot of researches based on RNN [ 48 ], LSTM [ 49 ], CNN [ 50 ] for sentiment analysis had been done, works based on sentiment embeddings also get excellent results [ 51 ] and will attract more and more attention.…”

Section: Related Workmentioning

confidence: 99%

Emotion computing using Word Mover’s Distance features based on Ren_CECps

Ren

Liu

2018

PLoS ONE

View full text Add to dashboard Cite

In this paper, we propose an emotion separated method(SeTF·IDF) to assign the emotion labels of sentences with different values, which has a better visual effect compared with the values represented by TF·IDF in the visualization of a multi-label Chinese emotional corpus Ren_CECps. Inspired by the enormous improvement of the visualization map propelled by the changed distances among the sentences, we being the first group utilizes the Word Mover’s Distance(WMD) algorithm as a way of feature representation in Chinese text emotion classification. Our experiments show that both in 80% for training, 20% for testing and 50% for training, 50% for testing experiments of Ren_CECps, WMD features get the best f1 scores and have a greater increase compared with the same dimension feature vectors obtained by dimension reduction TF·IDF method. Compared experiments in English corpus also show the efficiency of WMD features in the cross-language field.

show abstract

“…Kalchbrenner et al [7] proposed a K-MAX dynamic pooling model, which is different from the traditional pooling method and retains K important text features. Yangsen et al [8] applied RNN to the sentiment analysis of Chinese microblog corpus. By training the features vector with word and sentence information, it was finally proven that calculating the sentence vector can help learn the deep structure of the sentence.…”

Section: Introductionmentioning

confidence: 99%

Dual-Channel Attention Model for Text Sentiment Analysis

Li¹,

Zheng²,

Ren³

2019

IJPE

View full text Add to dashboard Cite

Focused on the issue that text information cannot be fully extracted by the single-channel neural network model, the Dual-Channel Attention Model (DCAM) is proposed for text sentiment analysis. Firstly, text is represented in the form of a matrix using a word vector trained by Word2Vec. Secondly, the matrix is used as input data and sent to Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) networks for feature extraction. Thirdly, an attention model is introduced to extract important feature information. Finally, the text features are merged, and the classification layer is used to classify the sentiment. The model is evaluated on a Chinese corpus. According to the experimental results, the accuracy of the proposed model can reach 92.7%, which is obviously superior to other single-channel neural network models.

show abstract

Study of Sentiment Classification for Chinese Microblog Based on Recurrent Neural Network

Cited by 42 publications

References 3 publications

Multi‐level Deep Correlative Networks for Multi‐modal Sentiment Analysis

Multi‐level Deep Correlative Networks for Multi‐modal Sentiment Analysis

Emotion computing using Word Mover’s Distance features based on Ren_CECps

Dual-Channel Attention Model for Text Sentiment Analysis

Contact Info

Product

Resources

About