Twitter sentiment analysis: A bootstrap ensemble framework

Ammar Hassan, Ahmed Abbasi, Dajun Zeng

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

70 Citations (Scopus)

Abstract

Twitter sentiment analysis has become widely popular. However, stable Twitter sentiment classification performance remains elusive due to several issues: heavy class imbalance in a multi-class problem, representational richness issues for sentiment cues, and the use of diverse colloquial linguistic patterns. These issues are problematic since many forms of social media analytics rely on accurate underlying Twitter sentiments. Accordingly, a text analytics framework is proposed for Twitter sentiment analysis. The framework uses an elaborate bootstrapping ensemble to quell class imbalance, sparsity, and representational richness issues. Experiment results reveal that the proposed approach is more accurate and balanced in its predictions across sentiment classes, as compared to various comparison tools and algorithms. Consequently, the bootstrapping ensemble framework is able to build sentiment time series that are better able to reflect events eliciting strong positive and negative sentiments from users. Considering the importance of Twitter as one of the premiere social media platforms, the results have important implications for social media analytics and social intelligence.

Original languageEnglish (US)
Title of host publicationProceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013
Pages357-364
Number of pages8
DOIs
StatePublished - 2013
Event2013 ASE/IEEE Int. Conf. on Social Computing, SocialCom 2013, the 2013 ASE/IEEE Int. Conf. on Big Data, BigData 2013, the 2013 Int. Conf. on Economic Computing, EconCom 2013, the 2013 PASSAT 2013, and the 2013 ASE/IEEE Int. Conf. on BioMedCom 2013 - Washington, DC, United States
Duration: Sep 8 2013Sep 14 2013

Other

Other2013 ASE/IEEE Int. Conf. on Social Computing, SocialCom 2013, the 2013 ASE/IEEE Int. Conf. on Big Data, BigData 2013, the 2013 Int. Conf. on Economic Computing, EconCom 2013, the 2013 PASSAT 2013, and the 2013 ASE/IEEE Int. Conf. on BioMedCom 2013
CountryUnited States
CityWashington, DC
Period9/8/139/14/13

Fingerprint

Linguistics
Time series
Experiments

Keywords

  • Machine learning
  • Opinion mining
  • Sentiment analysis
  • Social media analytics
  • Text mining

ASJC Scopus subject areas

  • Software

Cite this

Hassan, A., Abbasi, A., & Zeng, D. (2013). Twitter sentiment analysis: A bootstrap ensemble framework. In Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013 (pp. 357-364). [6693353] https://doi.org/10.1109/SocialCom.2013.56

Twitter sentiment analysis : A bootstrap ensemble framework. / Hassan, Ammar; Abbasi, Ahmed; Zeng, Dajun.

Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013. 2013. p. 357-364 6693353.

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

Hassan, A, Abbasi, A & Zeng, D 2013, Twitter sentiment analysis: A bootstrap ensemble framework. in Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013., 6693353, pp. 357-364, 2013 ASE/IEEE Int. Conf. on Social Computing, SocialCom 2013, the 2013 ASE/IEEE Int. Conf. on Big Data, BigData 2013, the 2013 Int. Conf. on Economic Computing, EconCom 2013, the 2013 PASSAT 2013, and the 2013 ASE/IEEE Int. Conf. on BioMedCom 2013, Washington, DC, United States, 9/8/13. https://doi.org/10.1109/SocialCom.2013.56
Hassan A, Abbasi A, Zeng D. Twitter sentiment analysis: A bootstrap ensemble framework. In Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013. 2013. p. 357-364. 6693353 https://doi.org/10.1109/SocialCom.2013.56
Hassan, Ammar ; Abbasi, Ahmed ; Zeng, Dajun. / Twitter sentiment analysis : A bootstrap ensemble framework. Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013. 2013. pp. 357-364
@inproceedings{92dc35e2527a431cb139348a3b288ba0,
title = "Twitter sentiment analysis: A bootstrap ensemble framework",
abstract = "Twitter sentiment analysis has become widely popular. However, stable Twitter sentiment classification performance remains elusive due to several issues: heavy class imbalance in a multi-class problem, representational richness issues for sentiment cues, and the use of diverse colloquial linguistic patterns. These issues are problematic since many forms of social media analytics rely on accurate underlying Twitter sentiments. Accordingly, a text analytics framework is proposed for Twitter sentiment analysis. The framework uses an elaborate bootstrapping ensemble to quell class imbalance, sparsity, and representational richness issues. Experiment results reveal that the proposed approach is more accurate and balanced in its predictions across sentiment classes, as compared to various comparison tools and algorithms. Consequently, the bootstrapping ensemble framework is able to build sentiment time series that are better able to reflect events eliciting strong positive and negative sentiments from users. Considering the importance of Twitter as one of the premiere social media platforms, the results have important implications for social media analytics and social intelligence.",
keywords = "Machine learning, Opinion mining, Sentiment analysis, Social media analytics, Text mining",
author = "Ammar Hassan and Ahmed Abbasi and Dajun Zeng",
year = "2013",
doi = "10.1109/SocialCom.2013.56",
language = "English (US)",
isbn = "9780769551371",
pages = "357--364",
booktitle = "Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013",

}

TY - GEN

T1 - Twitter sentiment analysis

T2 - A bootstrap ensemble framework

AU - Hassan, Ammar

AU - Abbasi, Ahmed

AU - Zeng, Dajun

PY - 2013

Y1 - 2013

N2 - Twitter sentiment analysis has become widely popular. However, stable Twitter sentiment classification performance remains elusive due to several issues: heavy class imbalance in a multi-class problem, representational richness issues for sentiment cues, and the use of diverse colloquial linguistic patterns. These issues are problematic since many forms of social media analytics rely on accurate underlying Twitter sentiments. Accordingly, a text analytics framework is proposed for Twitter sentiment analysis. The framework uses an elaborate bootstrapping ensemble to quell class imbalance, sparsity, and representational richness issues. Experiment results reveal that the proposed approach is more accurate and balanced in its predictions across sentiment classes, as compared to various comparison tools and algorithms. Consequently, the bootstrapping ensemble framework is able to build sentiment time series that are better able to reflect events eliciting strong positive and negative sentiments from users. Considering the importance of Twitter as one of the premiere social media platforms, the results have important implications for social media analytics and social intelligence.

AB - Twitter sentiment analysis has become widely popular. However, stable Twitter sentiment classification performance remains elusive due to several issues: heavy class imbalance in a multi-class problem, representational richness issues for sentiment cues, and the use of diverse colloquial linguistic patterns. These issues are problematic since many forms of social media analytics rely on accurate underlying Twitter sentiments. Accordingly, a text analytics framework is proposed for Twitter sentiment analysis. The framework uses an elaborate bootstrapping ensemble to quell class imbalance, sparsity, and representational richness issues. Experiment results reveal that the proposed approach is more accurate and balanced in its predictions across sentiment classes, as compared to various comparison tools and algorithms. Consequently, the bootstrapping ensemble framework is able to build sentiment time series that are better able to reflect events eliciting strong positive and negative sentiments from users. Considering the importance of Twitter as one of the premiere social media platforms, the results have important implications for social media analytics and social intelligence.

KW - Machine learning

KW - Opinion mining

KW - Sentiment analysis

KW - Social media analytics

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=84893603417&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893603417&partnerID=8YFLogxK

U2 - 10.1109/SocialCom.2013.56

DO - 10.1109/SocialCom.2013.56

M3 - Conference contribution

AN - SCOPUS:84893603417

SN - 9780769551371

SP - 357

EP - 364

BT - Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013

ER -