Crawling credible online medical sentiments for social intelligence

Ahmed Abbasi, Tianjun Fu, Dajun Zeng, Donald Adjeroh

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

12 Citations (Scopus)

Abstract

Social intelligence derived from Health 2.0 content has become of significant importance for various applications, including post-marketing drug surveillance, competitive intelligence, and to assess health-related opinions and sentiments. However, the volume, velocity, variety, and quality of online health information present challenges, necessitating enhanced facilitation mechanisms for medical social computing. In this study, we propose a focused crawler for online medical content. The crawler leverages enhanced credibility and context information. An extensive evaluation was performed against several comparison methods, on an online Health 2.0 test bed encompassing millions of pages. The results revealed that the proposed method was able to collect relevant content with considerably higher precision and recall rates than comparison methods, on content associated with medical websites, forums, blogs, and social networking sites. Furthermore, an example was used to illustrate the usefulness of the crawler for accurately representing online drug sentiments. Overall, the results have important implications for social computing, where a high-quality data and information foundation are imperative to the success of any overlying social intelligence initiative.

Original languageEnglish (US)
Title of host publicationProceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013
Pages254-263
Number of pages10
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

Health
Competitive intelligence
Blogs
Websites
Marketing

Keywords

  • Focused crawling
  • Sentiment analysis
  • Social intelligence
  • Social media analytics
  • Text mining
  • Web mining

ASJC Scopus subject areas

  • Software

Cite this

Abbasi, A., Fu, T., Zeng, D., & Adjeroh, D. (2013). Crawling credible online medical sentiments for social intelligence. In Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013 (pp. 254-263). [6693340] https://doi.org/10.1109/SocialCom.2013.43

Crawling credible online medical sentiments for social intelligence. / Abbasi, Ahmed; Fu, Tianjun; Zeng, Dajun; Adjeroh, Donald.

Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013. 2013. p. 254-263 6693340.

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

Abbasi, A, Fu, T, Zeng, D & Adjeroh, D 2013, Crawling credible online medical sentiments for social intelligence. in Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013., 6693340, pp. 254-263, 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.2013.43
Abbasi A, Fu T, Zeng D, Adjeroh D. Crawling credible online medical sentiments for social intelligence. In Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013. 2013. p. 254-263. 6693340 https://doi.org/10.1109/SocialCom.2013.43
Abbasi, Ahmed ; Fu, Tianjun ; Zeng, Dajun ; Adjeroh, Donald. / Crawling credible online medical sentiments for social intelligence. Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013. 2013. pp. 254-263
@inproceedings{4f7ce9b6bd7e49e6a8d3eaa72d5e0416,
title = "Crawling credible online medical sentiments for social intelligence",
abstract = "Social intelligence derived from Health 2.0 content has become of significant importance for various applications, including post-marketing drug surveillance, competitive intelligence, and to assess health-related opinions and sentiments. However, the volume, velocity, variety, and quality of online health information present challenges, necessitating enhanced facilitation mechanisms for medical social computing. In this study, we propose a focused crawler for online medical content. The crawler leverages enhanced credibility and context information. An extensive evaluation was performed against several comparison methods, on an online Health 2.0 test bed encompassing millions of pages. The results revealed that the proposed method was able to collect relevant content with considerably higher precision and recall rates than comparison methods, on content associated with medical websites, forums, blogs, and social networking sites. Furthermore, an example was used to illustrate the usefulness of the crawler for accurately representing online drug sentiments. Overall, the results have important implications for social computing, where a high-quality data and information foundation are imperative to the success of any overlying social intelligence initiative.",
keywords = "Focused crawling, Sentiment analysis, Social intelligence, Social media analytics, Text mining, Web mining",
author = "Ahmed Abbasi and Tianjun Fu and Dajun Zeng and Donald Adjeroh",
year = "2013",
doi = "10.1109/SocialCom.2013.43",
language = "English (US)",
isbn = "9780769551371",
pages = "254--263",
booktitle = "Proceedings - SocialCom/PASSAT/BigData/EconCom/BioMedCom 2013",

}

TY - GEN

T1 - Crawling credible online medical sentiments for social intelligence

AU - Abbasi, Ahmed

AU - Fu, Tianjun

AU - Zeng, Dajun

AU - Adjeroh, Donald

PY - 2013

Y1 - 2013

N2 - Social intelligence derived from Health 2.0 content has become of significant importance for various applications, including post-marketing drug surveillance, competitive intelligence, and to assess health-related opinions and sentiments. However, the volume, velocity, variety, and quality of online health information present challenges, necessitating enhanced facilitation mechanisms for medical social computing. In this study, we propose a focused crawler for online medical content. The crawler leverages enhanced credibility and context information. An extensive evaluation was performed against several comparison methods, on an online Health 2.0 test bed encompassing millions of pages. The results revealed that the proposed method was able to collect relevant content with considerably higher precision and recall rates than comparison methods, on content associated with medical websites, forums, blogs, and social networking sites. Furthermore, an example was used to illustrate the usefulness of the crawler for accurately representing online drug sentiments. Overall, the results have important implications for social computing, where a high-quality data and information foundation are imperative to the success of any overlying social intelligence initiative.

AB - Social intelligence derived from Health 2.0 content has become of significant importance for various applications, including post-marketing drug surveillance, competitive intelligence, and to assess health-related opinions and sentiments. However, the volume, velocity, variety, and quality of online health information present challenges, necessitating enhanced facilitation mechanisms for medical social computing. In this study, we propose a focused crawler for online medical content. The crawler leverages enhanced credibility and context information. An extensive evaluation was performed against several comparison methods, on an online Health 2.0 test bed encompassing millions of pages. The results revealed that the proposed method was able to collect relevant content with considerably higher precision and recall rates than comparison methods, on content associated with medical websites, forums, blogs, and social networking sites. Furthermore, an example was used to illustrate the usefulness of the crawler for accurately representing online drug sentiments. Overall, the results have important implications for social computing, where a high-quality data and information foundation are imperative to the success of any overlying social intelligence initiative.

KW - Focused crawling

KW - Sentiment analysis

KW - Social intelligence

KW - Social media analytics

KW - Text mining

KW - Web mining

UR - http://www.scopus.com/inward/record.url?scp=84893533709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893533709&partnerID=8YFLogxK

U2 - 10.1109/SocialCom.2013.43

DO - 10.1109/SocialCom.2013.43

M3 - Conference contribution

AN - SCOPUS:84893533709

SN - 9780769551371

SP - 254

EP - 263

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

ER -