Sentiment analysis of Chinese microblog message using neural network-based vector representation for measuring Regional prejudice

Yung Chun Chang, Chin Shun Chou, Yang Zhang, Xi Wang, Wen Lian Hsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Regional prejudice is prevalent in Chinese cities in which native residents and migrants lack a basic level of trust in the other group. Like Twitter, Sina Weibo is a social media platform where people actively engage in discussions on various social issues. Thus, it provides a good data source for measuring individuals' regional prejudice on a large scale. We find that a resentful tone dominates in Weibo messages related to migrants. In this paper, we propose a novel approach, named DKV, for recognizing polarity and direction of sentiment for Weibo messages using distributed real-valued vector representation of keywords learned from neural networks. Such a representation can project rich context information (or embedding) into the vector space, and subsequently be used to infer similarity measures among words, sentences, and even documents. We provide a comprehensive performance evaluation to demonstrate that by exploiting the keyword embeddings, DKV paired with support vector machines can effectively recognize a Weibo message into the predefined sentiment and its direction. Results demonstrate that our method can achieve the best performances compared to other approaches.

Original languageEnglish
Title of host publicationPacific Asia Conference on Information Systems, PACIS 2016 - Proceedings
PublisherPacific Asia Conference on Information Systems
ISBN (Electronic)9789860491029
Publication statusPublished - 2016
Externally publishedYes
Event20th Pacific Asia Conference on Information Systems, PACIS 2016 - Chiayi, Taiwan
Duration: Jun 27 2016Jul 1 2016

Conference

Conference20th Pacific Asia Conference on Information Systems, PACIS 2016
CountryTaiwan
CityChiayi
Period6/27/167/1/16

Fingerprint

Vector spaces
Support vector machines
Neural networks

Keywords

  • Distributed word representation
  • Neural network
  • Regional prejudice
  • Sentiment analysis
  • Text classification

ASJC Scopus subject areas

  • Information Systems

Cite this

Chang, Y. C., Chou, C. S., Zhang, Y., Wang, X., & Hsu, W. L. (2016). Sentiment analysis of Chinese microblog message using neural network-based vector representation for measuring Regional prejudice. In Pacific Asia Conference on Information Systems, PACIS 2016 - Proceedings Pacific Asia Conference on Information Systems.

Sentiment analysis of Chinese microblog message using neural network-based vector representation for measuring Regional prejudice. / Chang, Yung Chun; Chou, Chin Shun; Zhang, Yang; Wang, Xi; Hsu, Wen Lian.

Pacific Asia Conference on Information Systems, PACIS 2016 - Proceedings. Pacific Asia Conference on Information Systems, 2016.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chang, YC, Chou, CS, Zhang, Y, Wang, X & Hsu, WL 2016, Sentiment analysis of Chinese microblog message using neural network-based vector representation for measuring Regional prejudice. in Pacific Asia Conference on Information Systems, PACIS 2016 - Proceedings. Pacific Asia Conference on Information Systems, 20th Pacific Asia Conference on Information Systems, PACIS 2016, Chiayi, Taiwan, 6/27/16.
Chang YC, Chou CS, Zhang Y, Wang X, Hsu WL. Sentiment analysis of Chinese microblog message using neural network-based vector representation for measuring Regional prejudice. In Pacific Asia Conference on Information Systems, PACIS 2016 - Proceedings. Pacific Asia Conference on Information Systems. 2016
Chang, Yung Chun ; Chou, Chin Shun ; Zhang, Yang ; Wang, Xi ; Hsu, Wen Lian. / Sentiment analysis of Chinese microblog message using neural network-based vector representation for measuring Regional prejudice. Pacific Asia Conference on Information Systems, PACIS 2016 - Proceedings. Pacific Asia Conference on Information Systems, 2016.
@inproceedings{e606ba0010ba4917948b4d8e93571c1a,
title = "Sentiment analysis of Chinese microblog message using neural network-based vector representation for measuring Regional prejudice",
abstract = "Regional prejudice is prevalent in Chinese cities in which native residents and migrants lack a basic level of trust in the other group. Like Twitter, Sina Weibo is a social media platform where people actively engage in discussions on various social issues. Thus, it provides a good data source for measuring individuals' regional prejudice on a large scale. We find that a resentful tone dominates in Weibo messages related to migrants. In this paper, we propose a novel approach, named DKV, for recognizing polarity and direction of sentiment for Weibo messages using distributed real-valued vector representation of keywords learned from neural networks. Such a representation can project rich context information (or embedding) into the vector space, and subsequently be used to infer similarity measures among words, sentences, and even documents. We provide a comprehensive performance evaluation to demonstrate that by exploiting the keyword embeddings, DKV paired with support vector machines can effectively recognize a Weibo message into the predefined sentiment and its direction. Results demonstrate that our method can achieve the best performances compared to other approaches.",
keywords = "Distributed word representation, Neural network, Regional prejudice, Sentiment analysis, Text classification",
author = "Chang, {Yung Chun} and Chou, {Chin Shun} and Yang Zhang and Xi Wang and Hsu, {Wen Lian}",
year = "2016",
language = "English",
booktitle = "Pacific Asia Conference on Information Systems, PACIS 2016 - Proceedings",
publisher = "Pacific Asia Conference on Information Systems",

}

TY - GEN

T1 - Sentiment analysis of Chinese microblog message using neural network-based vector representation for measuring Regional prejudice

AU - Chang, Yung Chun

AU - Chou, Chin Shun

AU - Zhang, Yang

AU - Wang, Xi

AU - Hsu, Wen Lian

PY - 2016

Y1 - 2016

N2 - Regional prejudice is prevalent in Chinese cities in which native residents and migrants lack a basic level of trust in the other group. Like Twitter, Sina Weibo is a social media platform where people actively engage in discussions on various social issues. Thus, it provides a good data source for measuring individuals' regional prejudice on a large scale. We find that a resentful tone dominates in Weibo messages related to migrants. In this paper, we propose a novel approach, named DKV, for recognizing polarity and direction of sentiment for Weibo messages using distributed real-valued vector representation of keywords learned from neural networks. Such a representation can project rich context information (or embedding) into the vector space, and subsequently be used to infer similarity measures among words, sentences, and even documents. We provide a comprehensive performance evaluation to demonstrate that by exploiting the keyword embeddings, DKV paired with support vector machines can effectively recognize a Weibo message into the predefined sentiment and its direction. Results demonstrate that our method can achieve the best performances compared to other approaches.

AB - Regional prejudice is prevalent in Chinese cities in which native residents and migrants lack a basic level of trust in the other group. Like Twitter, Sina Weibo is a social media platform where people actively engage in discussions on various social issues. Thus, it provides a good data source for measuring individuals' regional prejudice on a large scale. We find that a resentful tone dominates in Weibo messages related to migrants. In this paper, we propose a novel approach, named DKV, for recognizing polarity and direction of sentiment for Weibo messages using distributed real-valued vector representation of keywords learned from neural networks. Such a representation can project rich context information (or embedding) into the vector space, and subsequently be used to infer similarity measures among words, sentences, and even documents. We provide a comprehensive performance evaluation to demonstrate that by exploiting the keyword embeddings, DKV paired with support vector machines can effectively recognize a Weibo message into the predefined sentiment and its direction. Results demonstrate that our method can achieve the best performances compared to other approaches.

KW - Distributed word representation

KW - Neural network

KW - Regional prejudice

KW - Sentiment analysis

KW - Text classification

UR - http://www.scopus.com/inward/record.url?scp=85011101300&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011101300&partnerID=8YFLogxK

M3 - Conference contribution

BT - Pacific Asia Conference on Information Systems, PACIS 2016 - Proceedings

PB - Pacific Asia Conference on Information Systems

ER -