Abstract

The explosion of social media services presents a great opportunity to understand the sentiment of the public via analyzing its large-scale and opinion-rich data. In social media, it is easy to amass vast quantities of unlabeled data, but very costly to obtain sentiment labels, which makes unsupervised sentiment analysis essential for various applications. It is challenging for traditional lexicon-based unsupervised methods due to the fact that expressions in social media are unstructured, informal, and fast-evolving. Emoticons and product ratings are examples of emotional signals that are associated with sentiments expressed in posts or words. Inspired by the wide availability of emotional signals in social media, we propose to study the problem of unsupervised sentiment analysis with emotional signals. In particular, we investigate whether the signals can potentially help sentiment analysis by providing a unified way to model two main categories of emotional signals, i.e., emotion indication and emotion correlation. We further incorporate the signals into an unsupervised learning framework for sentiment analysis. In the experiment, we compare the proposed framework with the state-of-the-art methods on two Twitter datasets and empirically evaluate our proposed framework to gain a deep understanding of the effects of emotional signals. Copyright is held by the International World Wide Web Conference Committee (IW3C2).

Original languageEnglish (US)
Title of host publicationWWW 2013 - Proceedings of the 22nd International Conference on World Wide Web
Pages607-617
Number of pages11
StatePublished - 2013
Event22nd International Conference on World Wide Web, WWW 2013 - Rio de Janeiro, Brazil
Duration: May 13 2013May 17 2013

Other

Other22nd International Conference on World Wide Web, WWW 2013
CountryBrazil
CityRio de Janeiro
Period5/13/135/17/13

Fingerprint

Unsupervised learning
World Wide Web
Explosions
Labels
Availability
Experiments

Keywords

  • Emoticon
  • Emotional signals
  • Sentiment analysis
  • Social correlation
  • Social media
  • Twitter

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Hu, X., Tang, J., Gao, H., & Liu, H. (2013). Unsupervised sentiment analysis with emotional signals. In WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web (pp. 607-617)

Unsupervised sentiment analysis with emotional signals. / Hu, Xia; Tang, Jiliang; Gao, Huiji; Liu, Huan.

WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web. 2013. p. 607-617.

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

Hu, X, Tang, J, Gao, H & Liu, H 2013, Unsupervised sentiment analysis with emotional signals. in WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web. pp. 607-617, 22nd International Conference on World Wide Web, WWW 2013, Rio de Janeiro, Brazil, 5/13/13.
Hu X, Tang J, Gao H, Liu H. Unsupervised sentiment analysis with emotional signals. In WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web. 2013. p. 607-617
Hu, Xia ; Tang, Jiliang ; Gao, Huiji ; Liu, Huan. / Unsupervised sentiment analysis with emotional signals. WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web. 2013. pp. 607-617
@inproceedings{e7ba262d204b4662b263de160b8caecb,
title = "Unsupervised sentiment analysis with emotional signals",
abstract = "The explosion of social media services presents a great opportunity to understand the sentiment of the public via analyzing its large-scale and opinion-rich data. In social media, it is easy to amass vast quantities of unlabeled data, but very costly to obtain sentiment labels, which makes unsupervised sentiment analysis essential for various applications. It is challenging for traditional lexicon-based unsupervised methods due to the fact that expressions in social media are unstructured, informal, and fast-evolving. Emoticons and product ratings are examples of emotional signals that are associated with sentiments expressed in posts or words. Inspired by the wide availability of emotional signals in social media, we propose to study the problem of unsupervised sentiment analysis with emotional signals. In particular, we investigate whether the signals can potentially help sentiment analysis by providing a unified way to model two main categories of emotional signals, i.e., emotion indication and emotion correlation. We further incorporate the signals into an unsupervised learning framework for sentiment analysis. In the experiment, we compare the proposed framework with the state-of-the-art methods on two Twitter datasets and empirically evaluate our proposed framework to gain a deep understanding of the effects of emotional signals. Copyright is held by the International World Wide Web Conference Committee (IW3C2).",
keywords = "Emoticon, Emotional signals, Sentiment analysis, Social correlation, Social media, Twitter",
author = "Xia Hu and Jiliang Tang and Huiji Gao and Huan Liu",
year = "2013",
language = "English (US)",
isbn = "9781450320351",
pages = "607--617",
booktitle = "WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web",

}

TY - GEN

T1 - Unsupervised sentiment analysis with emotional signals

AU - Hu, Xia

AU - Tang, Jiliang

AU - Gao, Huiji

AU - Liu, Huan

PY - 2013

Y1 - 2013

N2 - The explosion of social media services presents a great opportunity to understand the sentiment of the public via analyzing its large-scale and opinion-rich data. In social media, it is easy to amass vast quantities of unlabeled data, but very costly to obtain sentiment labels, which makes unsupervised sentiment analysis essential for various applications. It is challenging for traditional lexicon-based unsupervised methods due to the fact that expressions in social media are unstructured, informal, and fast-evolving. Emoticons and product ratings are examples of emotional signals that are associated with sentiments expressed in posts or words. Inspired by the wide availability of emotional signals in social media, we propose to study the problem of unsupervised sentiment analysis with emotional signals. In particular, we investigate whether the signals can potentially help sentiment analysis by providing a unified way to model two main categories of emotional signals, i.e., emotion indication and emotion correlation. We further incorporate the signals into an unsupervised learning framework for sentiment analysis. In the experiment, we compare the proposed framework with the state-of-the-art methods on two Twitter datasets and empirically evaluate our proposed framework to gain a deep understanding of the effects of emotional signals. Copyright is held by the International World Wide Web Conference Committee (IW3C2).

AB - The explosion of social media services presents a great opportunity to understand the sentiment of the public via analyzing its large-scale and opinion-rich data. In social media, it is easy to amass vast quantities of unlabeled data, but very costly to obtain sentiment labels, which makes unsupervised sentiment analysis essential for various applications. It is challenging for traditional lexicon-based unsupervised methods due to the fact that expressions in social media are unstructured, informal, and fast-evolving. Emoticons and product ratings are examples of emotional signals that are associated with sentiments expressed in posts or words. Inspired by the wide availability of emotional signals in social media, we propose to study the problem of unsupervised sentiment analysis with emotional signals. In particular, we investigate whether the signals can potentially help sentiment analysis by providing a unified way to model two main categories of emotional signals, i.e., emotion indication and emotion correlation. We further incorporate the signals into an unsupervised learning framework for sentiment analysis. In the experiment, we compare the proposed framework with the state-of-the-art methods on two Twitter datasets and empirically evaluate our proposed framework to gain a deep understanding of the effects of emotional signals. Copyright is held by the International World Wide Web Conference Committee (IW3C2).

KW - Emoticon

KW - Emotional signals

KW - Sentiment analysis

KW - Social correlation

KW - Social media

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84893144737&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893144737&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84893144737

SN - 9781450320351

SP - 607

EP - 617

BT - WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web

ER -