Abstract

Microblogging, like Twitter and Sina Weibo, has become a popular platform of human expressions, through which users can easily produce content on breaking news, public events, or products. The massive amount of microblogging data is a useful and timely source that carries mass sentiment and opinions on various topics. Existing sentiment analysis approaches often assume that texts are independent and identically distributed (i.i.d.), usually focusing on building a sophisticated feature space to handle noisy and short texts, without taking advantage of the fact that the microblogs are networked data. Inspired by the social sciences findings that sentiment consistency and emotional contagion are observed in social networks, we investigate whether social relations can help sentiment analysis by proposing a Sociological Approach to handling Noisy and short Texts (SANT) for sentiment classification. In particular, we present a mathematical optimization formulation that incorporates the sentiment consistency and emotional contagion theories into the supervised learning process; and utilize sparse learning to tackle noisy texts in microblogging. An empirical study of two real-world Twitter datasets shows the superior performance of our framework in handling noisy and short tweets.

Original languageEnglish (US)
Title of host publicationWSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining
Pages537-546
Number of pages10
DOIs
StatePublished - 2013
Event6th ACM International Conference on Web Search and Data Mining, WSDM 2013 - Rome, Italy
Duration: Feb 4 2013Feb 8 2013

Other

Other6th ACM International Conference on Web Search and Data Mining, WSDM 2013
CountryItaly
CityRome
Period2/4/132/8/13

Fingerprint

Social sciences
Supervised learning

Keywords

  • microblogging
  • noisy text
  • sentiment analysis
  • sentiment classification
  • short text
  • social context
  • social correlation
  • twitter

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Hu, X., Tang, L., Tang, J., & Liu, H. (2013). Exploiting social relations for sentiment analysis in microblogging. In WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining (pp. 537-546) https://doi.org/10.1145/2433396.2433465

Exploiting social relations for sentiment analysis in microblogging. / Hu, Xia; Tang, Lei; Tang, Jiliang; Liu, Huan.

WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining. 2013. p. 537-546.

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

Hu, X, Tang, L, Tang, J & Liu, H 2013, Exploiting social relations for sentiment analysis in microblogging. in WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining. pp. 537-546, 6th ACM International Conference on Web Search and Data Mining, WSDM 2013, Rome, Italy, 2/4/13. https://doi.org/10.1145/2433396.2433465
Hu X, Tang L, Tang J, Liu H. Exploiting social relations for sentiment analysis in microblogging. In WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining. 2013. p. 537-546 https://doi.org/10.1145/2433396.2433465
Hu, Xia ; Tang, Lei ; Tang, Jiliang ; Liu, Huan. / Exploiting social relations for sentiment analysis in microblogging. WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining. 2013. pp. 537-546
@inproceedings{9256f64e65ad43a888fb61ffd34ba3ac,
title = "Exploiting social relations for sentiment analysis in microblogging",
abstract = "Microblogging, like Twitter and Sina Weibo, has become a popular platform of human expressions, through which users can easily produce content on breaking news, public events, or products. The massive amount of microblogging data is a useful and timely source that carries mass sentiment and opinions on various topics. Existing sentiment analysis approaches often assume that texts are independent and identically distributed (i.i.d.), usually focusing on building a sophisticated feature space to handle noisy and short texts, without taking advantage of the fact that the microblogs are networked data. Inspired by the social sciences findings that sentiment consistency and emotional contagion are observed in social networks, we investigate whether social relations can help sentiment analysis by proposing a Sociological Approach to handling Noisy and short Texts (SANT) for sentiment classification. In particular, we present a mathematical optimization formulation that incorporates the sentiment consistency and emotional contagion theories into the supervised learning process; and utilize sparse learning to tackle noisy texts in microblogging. An empirical study of two real-world Twitter datasets shows the superior performance of our framework in handling noisy and short tweets.",
keywords = "microblogging, noisy text, sentiment analysis, sentiment classification, short text, social context, social correlation, twitter",
author = "Xia Hu and Lei Tang and Jiliang Tang and Huan Liu",
year = "2013",
doi = "10.1145/2433396.2433465",
language = "English (US)",
isbn = "9781450318693",
pages = "537--546",
booktitle = "WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining",

}

TY - GEN

T1 - Exploiting social relations for sentiment analysis in microblogging

AU - Hu, Xia

AU - Tang, Lei

AU - Tang, Jiliang

AU - Liu, Huan

PY - 2013

Y1 - 2013

N2 - Microblogging, like Twitter and Sina Weibo, has become a popular platform of human expressions, through which users can easily produce content on breaking news, public events, or products. The massive amount of microblogging data is a useful and timely source that carries mass sentiment and opinions on various topics. Existing sentiment analysis approaches often assume that texts are independent and identically distributed (i.i.d.), usually focusing on building a sophisticated feature space to handle noisy and short texts, without taking advantage of the fact that the microblogs are networked data. Inspired by the social sciences findings that sentiment consistency and emotional contagion are observed in social networks, we investigate whether social relations can help sentiment analysis by proposing a Sociological Approach to handling Noisy and short Texts (SANT) for sentiment classification. In particular, we present a mathematical optimization formulation that incorporates the sentiment consistency and emotional contagion theories into the supervised learning process; and utilize sparse learning to tackle noisy texts in microblogging. An empirical study of two real-world Twitter datasets shows the superior performance of our framework in handling noisy and short tweets.

AB - Microblogging, like Twitter and Sina Weibo, has become a popular platform of human expressions, through which users can easily produce content on breaking news, public events, or products. The massive amount of microblogging data is a useful and timely source that carries mass sentiment and opinions on various topics. Existing sentiment analysis approaches often assume that texts are independent and identically distributed (i.i.d.), usually focusing on building a sophisticated feature space to handle noisy and short texts, without taking advantage of the fact that the microblogs are networked data. Inspired by the social sciences findings that sentiment consistency and emotional contagion are observed in social networks, we investigate whether social relations can help sentiment analysis by proposing a Sociological Approach to handling Noisy and short Texts (SANT) for sentiment classification. In particular, we present a mathematical optimization formulation that incorporates the sentiment consistency and emotional contagion theories into the supervised learning process; and utilize sparse learning to tackle noisy texts in microblogging. An empirical study of two real-world Twitter datasets shows the superior performance of our framework in handling noisy and short tweets.

KW - microblogging

KW - noisy text

KW - sentiment analysis

KW - sentiment classification

KW - short text

KW - social context

KW - social correlation

KW - twitter

UR - http://www.scopus.com/inward/record.url?scp=84874258367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874258367&partnerID=8YFLogxK

U2 - 10.1145/2433396.2433465

DO - 10.1145/2433396.2433465

M3 - Conference contribution

AN - SCOPUS:84874258367

SN - 9781450318693

SP - 537

EP - 546

BT - WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining

ER -