Identifying leaders in an online cancer survivor community

Kang Zhao, Baojun Qiu, Cornelia Caragea, Dinghao Wu, Prasenjit Mitra, John Yen, Greta E. Greer, Kenneth Portier

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

8 Citations (Scopus)

Abstract

Online communities are an important source of social support for cancer survivors and their informal caregivers. This research attempts to identify leaders in a popular online forum for cancer survivors and caregivers using classification techniques. We extracted user features from many different perspectives, including user-contribution, network, and semantic features. Based on these features, we further utilized the structure of the network among users and generated new neighborhood-based and cluster-based features. Classification results revealed that these features are discriminative for leader identification. Using these features, we developed a hybrid approach based on an ensemble classifier that performs better than many traditional metrics. This research has important implications for understanding and managing similar online communities.

Original languageEnglish
Title of host publicationProceedings - 21st Workshop on Information Technologies and Systems, WITS 2011
PublisherJindal School of Management, JSOM
Pages115-120
Number of pages6
Publication statusPublished - 2011
Externally publishedYes
Event21st Workshop on Information Technologies and Systems, WITS 2011 - Shanghai
Duration: 3 Dec 20114 Dec 2011

Other

Other21st Workshop on Information Technologies and Systems, WITS 2011
CityShanghai
Period3/12/114/12/11

Fingerprint

Classifiers
Semantics

ASJC Scopus subject areas

  • Information Systems

Cite this

Zhao, K., Qiu, B., Caragea, C., Wu, D., Mitra, P., Yen, J., ... Portier, K. (2011). Identifying leaders in an online cancer survivor community. In Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011 (pp. 115-120). Jindal School of Management, JSOM.

Identifying leaders in an online cancer survivor community. / Zhao, Kang; Qiu, Baojun; Caragea, Cornelia; Wu, Dinghao; Mitra, Prasenjit; Yen, John; Greer, Greta E.; Portier, Kenneth.

Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011. Jindal School of Management, JSOM, 2011. p. 115-120.

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

Zhao, K, Qiu, B, Caragea, C, Wu, D, Mitra, P, Yen, J, Greer, GE & Portier, K 2011, Identifying leaders in an online cancer survivor community. in Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011. Jindal School of Management, JSOM, pp. 115-120, 21st Workshop on Information Technologies and Systems, WITS 2011, Shanghai, 3/12/11.
Zhao K, Qiu B, Caragea C, Wu D, Mitra P, Yen J et al. Identifying leaders in an online cancer survivor community. In Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011. Jindal School of Management, JSOM. 2011. p. 115-120
Zhao, Kang ; Qiu, Baojun ; Caragea, Cornelia ; Wu, Dinghao ; Mitra, Prasenjit ; Yen, John ; Greer, Greta E. ; Portier, Kenneth. / Identifying leaders in an online cancer survivor community. Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011. Jindal School of Management, JSOM, 2011. pp. 115-120
@inproceedings{add50368b675465aae2a155b98b22efe,
title = "Identifying leaders in an online cancer survivor community",
abstract = "Online communities are an important source of social support for cancer survivors and their informal caregivers. This research attempts to identify leaders in a popular online forum for cancer survivors and caregivers using classification techniques. We extracted user features from many different perspectives, including user-contribution, network, and semantic features. Based on these features, we further utilized the structure of the network among users and generated new neighborhood-based and cluster-based features. Classification results revealed that these features are discriminative for leader identification. Using these features, we developed a hybrid approach based on an ensemble classifier that performs better than many traditional metrics. This research has important implications for understanding and managing similar online communities.",
author = "Kang Zhao and Baojun Qiu and Cornelia Caragea and Dinghao Wu and Prasenjit Mitra and John Yen and Greer, {Greta E.} and Kenneth Portier",
year = "2011",
language = "English",
pages = "115--120",
booktitle = "Proceedings - 21st Workshop on Information Technologies and Systems, WITS 2011",
publisher = "Jindal School of Management, JSOM",

}

TY - GEN

T1 - Identifying leaders in an online cancer survivor community

AU - Zhao, Kang

AU - Qiu, Baojun

AU - Caragea, Cornelia

AU - Wu, Dinghao

AU - Mitra, Prasenjit

AU - Yen, John

AU - Greer, Greta E.

AU - Portier, Kenneth

PY - 2011

Y1 - 2011

N2 - Online communities are an important source of social support for cancer survivors and their informal caregivers. This research attempts to identify leaders in a popular online forum for cancer survivors and caregivers using classification techniques. We extracted user features from many different perspectives, including user-contribution, network, and semantic features. Based on these features, we further utilized the structure of the network among users and generated new neighborhood-based and cluster-based features. Classification results revealed that these features are discriminative for leader identification. Using these features, we developed a hybrid approach based on an ensemble classifier that performs better than many traditional metrics. This research has important implications for understanding and managing similar online communities.

AB - Online communities are an important source of social support for cancer survivors and their informal caregivers. This research attempts to identify leaders in a popular online forum for cancer survivors and caregivers using classification techniques. We extracted user features from many different perspectives, including user-contribution, network, and semantic features. Based on these features, we further utilized the structure of the network among users and generated new neighborhood-based and cluster-based features. Classification results revealed that these features are discriminative for leader identification. Using these features, we developed a hybrid approach based on an ensemble classifier that performs better than many traditional metrics. This research has important implications for understanding and managing similar online communities.

UR - http://www.scopus.com/inward/record.url?scp=84885924111&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885924111&partnerID=8YFLogxK

M3 - Conference contribution

SP - 115

EP - 120

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

PB - Jindal School of Management, JSOM

ER -