Combining opinion mining with social network analysis in opinion leader identification

Dajun Zeng, Hengmin Zhou, Yilu Zhou

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

Abstract

The increasing popularity of social networking websites facilitates expressing people's personal opinions in these Web 2.0 online channels. While social network analysis has been an important approach in opinion leader identification, actual opinions expressed in online communities have not been taken into consideration during this process. We propose Opinion Rank to enrich traditional social network analysis by incorporating sentiment of opinions mined from online user-generated content. In addition, we incorporate Opinion Rank with traditional node-based ranking to identify opinion leaders. Our experiments on real-world datasets of online reviews show that a hybrid approach combining both members' activity scores and Opinion Rank scores achieved the best performance in finding opinion leaders in large networks. Our study bridges two research areas, opinion mining and social network analysis, and demonstrates that sentiments among members can provide important clues for identifying experts or authorities in online communities.

Original languageEnglish (US)
Title of host publicationProceedings - 21st Workshop on Information Technologies and Systems, WITS 2011
PublisherJindal School of Management, JSOM
Pages157-162
Number of pages6
StatePublished - 2011
Event21st Workshop on Information Technologies and Systems, WITS 2011 - Shanghai, China
Duration: Dec 3 2011Dec 4 2011

Other

Other21st Workshop on Information Technologies and Systems, WITS 2011
CountryChina
CityShanghai
Period12/3/1112/4/11

Fingerprint

Electric network analysis
World Wide Web
Websites
Experiments

ASJC Scopus subject areas

  • Information Systems

Cite this

Zeng, D., Zhou, H., & Zhou, Y. (2011). Combining opinion mining with social network analysis in opinion leader identification. In Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011 (pp. 157-162). Jindal School of Management, JSOM.

Combining opinion mining with social network analysis in opinion leader identification. / Zeng, Dajun; Zhou, Hengmin; Zhou, Yilu.

Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011. Jindal School of Management, JSOM, 2011. p. 157-162.

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

Zeng, D, Zhou, H & Zhou, Y 2011, Combining opinion mining with social network analysis in opinion leader identification. in Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011. Jindal School of Management, JSOM, pp. 157-162, 21st Workshop on Information Technologies and Systems, WITS 2011, Shanghai, China, 12/3/11.
Zeng D, Zhou H, Zhou Y. Combining opinion mining with social network analysis in opinion leader identification. In Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011. Jindal School of Management, JSOM. 2011. p. 157-162
Zeng, Dajun ; Zhou, Hengmin ; Zhou, Yilu. / Combining opinion mining with social network analysis in opinion leader identification. Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011. Jindal School of Management, JSOM, 2011. pp. 157-162
@inproceedings{ff3f40e7c89b4ad2b033e55d01102bf9,
title = "Combining opinion mining with social network analysis in opinion leader identification",
abstract = "The increasing popularity of social networking websites facilitates expressing people's personal opinions in these Web 2.0 online channels. While social network analysis has been an important approach in opinion leader identification, actual opinions expressed in online communities have not been taken into consideration during this process. We propose Opinion Rank to enrich traditional social network analysis by incorporating sentiment of opinions mined from online user-generated content. In addition, we incorporate Opinion Rank with traditional node-based ranking to identify opinion leaders. Our experiments on real-world datasets of online reviews show that a hybrid approach combining both members' activity scores and Opinion Rank scores achieved the best performance in finding opinion leaders in large networks. Our study bridges two research areas, opinion mining and social network analysis, and demonstrates that sentiments among members can provide important clues for identifying experts or authorities in online communities.",
author = "Dajun Zeng and Hengmin Zhou and Yilu Zhou",
year = "2011",
language = "English (US)",
pages = "157--162",
booktitle = "Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011",
publisher = "Jindal School of Management, JSOM",

}

TY - GEN

T1 - Combining opinion mining with social network analysis in opinion leader identification

AU - Zeng, Dajun

AU - Zhou, Hengmin

AU - Zhou, Yilu

PY - 2011

Y1 - 2011

N2 - The increasing popularity of social networking websites facilitates expressing people's personal opinions in these Web 2.0 online channels. While social network analysis has been an important approach in opinion leader identification, actual opinions expressed in online communities have not been taken into consideration during this process. We propose Opinion Rank to enrich traditional social network analysis by incorporating sentiment of opinions mined from online user-generated content. In addition, we incorporate Opinion Rank with traditional node-based ranking to identify opinion leaders. Our experiments on real-world datasets of online reviews show that a hybrid approach combining both members' activity scores and Opinion Rank scores achieved the best performance in finding opinion leaders in large networks. Our study bridges two research areas, opinion mining and social network analysis, and demonstrates that sentiments among members can provide important clues for identifying experts or authorities in online communities.

AB - The increasing popularity of social networking websites facilitates expressing people's personal opinions in these Web 2.0 online channels. While social network analysis has been an important approach in opinion leader identification, actual opinions expressed in online communities have not been taken into consideration during this process. We propose Opinion Rank to enrich traditional social network analysis by incorporating sentiment of opinions mined from online user-generated content. In addition, we incorporate Opinion Rank with traditional node-based ranking to identify opinion leaders. Our experiments on real-world datasets of online reviews show that a hybrid approach combining both members' activity scores and Opinion Rank scores achieved the best performance in finding opinion leaders in large networks. Our study bridges two research areas, opinion mining and social network analysis, and demonstrates that sentiments among members can provide important clues for identifying experts or authorities in online communities.

UR - http://www.scopus.com/inward/record.url?scp=84901746881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901746881&partnerID=8YFLogxK

M3 - Conference contribution

SP - 157

EP - 162

BT - Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011

PB - Jindal School of Management, JSOM

ER -