Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM

Yue Lu; Junhao Zhou; Hong-Ning Dai; Hao Wang; Hong Xiao

doi:10.1109/I-SPAN.2018.00034

Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM

Yue Lu, Junhao Zhou, Hong-Ning Dai, Hao Wang, Hong Xiao

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

5 Citations (Scopus)

Abstract

In this paper, we propose a sentiment analysis method by incorporating Continuous Bag-of-Words (CBOW) model and Stacked Bidirectional long short-term memory (Stacked Bi-LSTM) model to enhance the performance of sentiment prediction. Firstly, a word embedding model, CBOW model, is employed to capture semantic features of words and transfer words into high dimensional word vectors. Secondly, we introduce Stacked Bi-LSTM model to conduct the feature extraction of sequential word vectors at a deep level. Finally, a binary softmax classifier utilizes semantic and contextual features to predict the sentiment orientation. Extensive experiments on real dataset collected from Weibo (i.e., one of the most popular Chinese microblogs) show that our proposed approach achieves better performance than other machine learning models.

Original language	English
Title of host publication	Proceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018
Publisher	IEEE
Pages	162-167
Number of pages	6
Edition	1st
ISBN (Electronic)	9781538685341
ISBN (Print)	9781538685358
DOIs	https://doi.org/10.1109/I-SPAN.2018.00034
Publication status	Published - 16 Oct 2018
Event	15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018 - Yichang, China Duration: 16 Oct 2018 → 18 Oct 2018 https://ieeexplore.ieee.org/xpl/conhome/8620718/proceeding (Conference proceedings)

Publication series

Name	Proceedings - International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN

Conference

Conference	15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018
Country/Territory	China
City	Yichang
Period	16/10/18 → 18/10/18
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8620718/proceeding (Conference proceedings)

User-Defined Keywords

Long short term memory (LSTM)
Stacked bi directional LSTM
Sentiment analysis
Continuous Bag of Words
Chinese MicroBlog

Access to Document

10.1109/I-SPAN.2018.00034

Cite this

Lu, Y., Zhou, J., Dai, H.-N., Wang, H., & Xiao, H. (2018). Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM. In Proceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018 (1st ed., pp. 162-167). (Proceedings - International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN). IEEE. https://doi.org/10.1109/I-SPAN.2018.00034

@inproceedings{e27f70f59bff434089070ac7f59b7818,

title = "Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM",

abstract = "In this paper, we propose a sentiment analysis method by incorporating Continuous Bag-of-Words (CBOW) model and Stacked Bidirectional long short-term memory (Stacked Bi-LSTM) model to enhance the performance of sentiment prediction. Firstly, a word embedding model, CBOW model, is employed to capture semantic features of words and transfer words into high dimensional word vectors. Secondly, we introduce Stacked Bi-LSTM model to conduct the feature extraction of sequential word vectors at a deep level. Finally, a binary softmax classifier utilizes semantic and contextual features to predict the sentiment orientation. Extensive experiments on real dataset collected from Weibo (i.e., one of the most popular Chinese microblogs) show that our proposed approach achieves better performance than other machine learning models.",

keywords = "Long short term memory (LSTM), Stacked bi directional LSTM, Sentiment analysis, Continuous Bag of Words, Chinese MicroBlog",

author = "Yue Lu and Junhao Zhou and Hong-Ning Dai and Hao Wang and Hong Xiao",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018 ; Conference date: 16-10-2018 Through 18-10-2018",

year = "2018",

month = oct,

day = "16",

doi = "10.1109/I-SPAN.2018.00034",

language = "English",

isbn = "9781538685358",

series = "Proceedings - International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN",

publisher = "IEEE",

pages = "162--167",

booktitle = "Proceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018",

address = "United States",

edition = "1st",

url = "https://ieeexplore.ieee.org/xpl/conhome/8620718/proceeding",

}

Lu, Y, Zhou, J, Dai, H-N, Wang, H & Xiao, H 2018, Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM. in Proceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018. 1st edn, Proceedings - International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN, IEEE, pp. 162-167, 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018, Yichang, China, 16/10/18. https://doi.org/10.1109/I-SPAN.2018.00034

Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM. / Lu, Yue; Zhou, Junhao; Dai, Hong-Ning et al.
Proceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018. 1st. ed. IEEE, 2018. p. 162-167 (Proceedings - International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM

AU - Lu, Yue

AU - Zhou, Junhao

AU - Dai, Hong-Ning

AU - Wang, Hao

AU - Xiao, Hong

PY - 2018/10/16

Y1 - 2018/10/16

N2 - In this paper, we propose a sentiment analysis method by incorporating Continuous Bag-of-Words (CBOW) model and Stacked Bidirectional long short-term memory (Stacked Bi-LSTM) model to enhance the performance of sentiment prediction. Firstly, a word embedding model, CBOW model, is employed to capture semantic features of words and transfer words into high dimensional word vectors. Secondly, we introduce Stacked Bi-LSTM model to conduct the feature extraction of sequential word vectors at a deep level. Finally, a binary softmax classifier utilizes semantic and contextual features to predict the sentiment orientation. Extensive experiments on real dataset collected from Weibo (i.e., one of the most popular Chinese microblogs) show that our proposed approach achieves better performance than other machine learning models.

AB - In this paper, we propose a sentiment analysis method by incorporating Continuous Bag-of-Words (CBOW) model and Stacked Bidirectional long short-term memory (Stacked Bi-LSTM) model to enhance the performance of sentiment prediction. Firstly, a word embedding model, CBOW model, is employed to capture semantic features of words and transfer words into high dimensional word vectors. Secondly, we introduce Stacked Bi-LSTM model to conduct the feature extraction of sequential word vectors at a deep level. Finally, a binary softmax classifier utilizes semantic and contextual features to predict the sentiment orientation. Extensive experiments on real dataset collected from Weibo (i.e., one of the most popular Chinese microblogs) show that our proposed approach achieves better performance than other machine learning models.

KW - Long short term memory (LSTM)

KW - Stacked bi directional LSTM

KW - Sentiment analysis

KW - Continuous Bag of Words

KW - Chinese MicroBlog

UR - http://www.scopus.com/inward/record.url?scp=85063688850&partnerID=8YFLogxK

U2 - 10.1109/I-SPAN.2018.00034

DO - 10.1109/I-SPAN.2018.00034

M3 - Conference proceeding

AN - SCOPUS:85063688850

SN - 9781538685358

T3 - Proceedings - International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN

SP - 162

EP - 167

BT - Proceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018

PB - IEEE

T2 - 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018

Y2 - 16 October 2018 through 18 October 2018

ER -

Lu Y, Zhou J, Dai HN, Wang H, Xiao H. Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM. In Proceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018. 1st ed. IEEE. 2018. p. 162-167. (Proceedings - International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN). doi: 10.1109/I-SPAN.2018.00034

Sentiment analysis of Chinese microblog based on stacked bidirectional LSTM

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this