Evaluating the usefulness of sentiment information for focused crawlers

Tianjun Fu; Ahmed Abbasi; Daniel Dajun Zeng; Hsinchun Chen

Evaluating the usefulness of sentiment information for focused crawlers

Tianjun Fu, Ahmed Abbasi, Daniel Dajun Zeng, Hsinchun Chen

Research output: Contribution to conference › Paper › peer-review

Abstract

Despite the prevalence of sentiment-related content on the Web, there has been limited work on focused crawlers capable of effectively collecting such content. In this study, we evaluated the efficacy of using sentiment-related information for enhanced focused crawling of opinion-rich web content regarding a particular topic. We also assessed the impact of using sentiment-labelled web graphs to further improve collection accuracy. Experimental results on a large testbed encompassing over half a million web pages revealed that focused crawlers utilizing sentiment information as well as sentiment-labelled web graphs are capable of gathering more holistic collections of opinion-related content regarding a particular topic. The results have important implications for business and marketing intelligence gathering efforts in the Web 2.0 era.

Original language	English (US)
State	Published - 2010
Event	20th Annual Workshop on Information Technologies and Systems, WITS 2010 - St. Louis, MO, United States Duration: Dec 11 2010 → Dec 12 2010

Other

Other	20th Annual Workshop on Information Technologies and Systems, WITS 2010
Country/Territory	United States
City	St. Louis, MO
Period	12/11/10 → 12/12/10

Keywords

Focused crawler
Labelled web graph
Sentiment analysis

ASJC Scopus subject areas

Information Systems

Cite this

@conference{9a871f96054e4d0b881d91866e2ee306,

title = "Evaluating the usefulness of sentiment information for focused crawlers",

abstract = "Despite the prevalence of sentiment-related content on the Web, there has been limited work on focused crawlers capable of effectively collecting such content. In this study, we evaluated the efficacy of using sentiment-related information for enhanced focused crawling of opinion-rich web content regarding a particular topic. We also assessed the impact of using sentiment-labelled web graphs to further improve collection accuracy. Experimental results on a large testbed encompassing over half a million web pages revealed that focused crawlers utilizing sentiment information as well as sentiment-labelled web graphs are capable of gathering more holistic collections of opinion-related content regarding a particular topic. The results have important implications for business and marketing intelligence gathering efforts in the Web 2.0 era.",

keywords = "Focused crawler, Labelled web graph, Sentiment analysis",

author = "Tianjun Fu and Ahmed Abbasi and Zeng, {Daniel Dajun} and Hsinchun Chen",

year = "2010",

language = "English (US)",

note = "20th Annual Workshop on Information Technologies and Systems, WITS 2010 ; Conference date: 11-12-2010 Through 12-12-2010",

}

TY - CONF

T1 - Evaluating the usefulness of sentiment information for focused crawlers

AU - Fu, Tianjun

AU - Abbasi, Ahmed

AU - Zeng, Daniel Dajun

AU - Chen, Hsinchun

PY - 2010

Y1 - 2010

N2 - Despite the prevalence of sentiment-related content on the Web, there has been limited work on focused crawlers capable of effectively collecting such content. In this study, we evaluated the efficacy of using sentiment-related information for enhanced focused crawling of opinion-rich web content regarding a particular topic. We also assessed the impact of using sentiment-labelled web graphs to further improve collection accuracy. Experimental results on a large testbed encompassing over half a million web pages revealed that focused crawlers utilizing sentiment information as well as sentiment-labelled web graphs are capable of gathering more holistic collections of opinion-related content regarding a particular topic. The results have important implications for business and marketing intelligence gathering efforts in the Web 2.0 era.

AB - Despite the prevalence of sentiment-related content on the Web, there has been limited work on focused crawlers capable of effectively collecting such content. In this study, we evaluated the efficacy of using sentiment-related information for enhanced focused crawling of opinion-rich web content regarding a particular topic. We also assessed the impact of using sentiment-labelled web graphs to further improve collection accuracy. Experimental results on a large testbed encompassing over half a million web pages revealed that focused crawlers utilizing sentiment information as well as sentiment-labelled web graphs are capable of gathering more holistic collections of opinion-related content regarding a particular topic. The results have important implications for business and marketing intelligence gathering efforts in the Web 2.0 era.

KW - Focused crawler

KW - Labelled web graph

KW - Sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=84900416626&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900416626&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84900416626

T2 - 20th Annual Workshop on Information Technologies and Systems, WITS 2010

Y2 - 11 December 2010 through 12 December 2010

ER -

Evaluating the usefulness of sentiment information for focused crawlers

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this