Predicting potential responders in social Q&A based on non-QA features

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

3 Citations (Scopus)

Abstract

Given the recent advancement of online social networking technologies, social question and answering has become an important venue for individuals to seek and share information. While studies have suggested the possibilities of routing questions to potential answerers for their help and the information provided, there is little analysis proposed to identify the characteristics that differentiate the possible responders from the nonresponders. In order to address such gap, in this work we present a model to predict potential responders in social Q&A using only non-QA-based attributes. We build the classifier using features from two different aspects, including: features extracted from one's social profile and style of posting. To evaluate our model, we collect over 20, 000 questions posted on Wenwo, a social Q&A application based on Weibo, along with all their responders. Our experimental results over the collected dataset demonstrate the effectiveness of responder prediction based on non-QA features and proposed potential implications for system design.

Original languageEnglish
Title of host publicationConference on Human Factors in Computing Systems - Proceedings
PublisherAssociation for Computing Machinery
Pages2131-2136
Number of pages6
ISBN (Print)9781450324748
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event32nd Annual ACM Conference on Human Factors in Computing Systems, CHI EA 2014 - Toronto, ON
Duration: 26 Apr 20141 May 2014

Other

Other32nd Annual ACM Conference on Human Factors in Computing Systems, CHI EA 2014
CityToronto, ON
Period26/4/141/5/14

Fingerprint

Classifiers
Systems analysis

Keywords

  • Information seeking
  • Social networks
  • Social Q&A
  • Social question and answering
  • Social search
  • Weibo

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Liu, Z., & Jansen, B. (2014). Predicting potential responders in social Q&A based on non-QA features. In Conference on Human Factors in Computing Systems - Proceedings (pp. 2131-2136). Association for Computing Machinery. https://doi.org/10.1145/2559206.2581366

Predicting potential responders in social Q&A based on non-QA features. / Liu, Zhe; Jansen, Bernard.

Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery, 2014. p. 2131-2136.

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

Liu, Z & Jansen, B 2014, Predicting potential responders in social Q&A based on non-QA features. in Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery, pp. 2131-2136, 32nd Annual ACM Conference on Human Factors in Computing Systems, CHI EA 2014, Toronto, ON, 26/4/14. https://doi.org/10.1145/2559206.2581366
Liu Z, Jansen B. Predicting potential responders in social Q&A based on non-QA features. In Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery. 2014. p. 2131-2136 https://doi.org/10.1145/2559206.2581366
Liu, Zhe ; Jansen, Bernard. / Predicting potential responders in social Q&A based on non-QA features. Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery, 2014. pp. 2131-2136
@inproceedings{a4cf377d7488451eaa1b6a13f040f230,
title = "Predicting potential responders in social Q&A based on non-QA features",
abstract = "Given the recent advancement of online social networking technologies, social question and answering has become an important venue for individuals to seek and share information. While studies have suggested the possibilities of routing questions to potential answerers for their help and the information provided, there is little analysis proposed to identify the characteristics that differentiate the possible responders from the nonresponders. In order to address such gap, in this work we present a model to predict potential responders in social Q&A using only non-QA-based attributes. We build the classifier using features from two different aspects, including: features extracted from one's social profile and style of posting. To evaluate our model, we collect over 20, 000 questions posted on Wenwo, a social Q&A application based on Weibo, along with all their responders. Our experimental results over the collected dataset demonstrate the effectiveness of responder prediction based on non-QA features and proposed potential implications for system design.",
keywords = "Information seeking, Social networks, Social Q&A, Social question and answering, Social search, Weibo",
author = "Zhe Liu and Bernard Jansen",
year = "2014",
doi = "10.1145/2559206.2581366",
language = "English",
isbn = "9781450324748",
pages = "2131--2136",
booktitle = "Conference on Human Factors in Computing Systems - Proceedings",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Predicting potential responders in social Q&A based on non-QA features

AU - Liu, Zhe

AU - Jansen, Bernard

PY - 2014

Y1 - 2014

N2 - Given the recent advancement of online social networking technologies, social question and answering has become an important venue for individuals to seek and share information. While studies have suggested the possibilities of routing questions to potential answerers for their help and the information provided, there is little analysis proposed to identify the characteristics that differentiate the possible responders from the nonresponders. In order to address such gap, in this work we present a model to predict potential responders in social Q&A using only non-QA-based attributes. We build the classifier using features from two different aspects, including: features extracted from one's social profile and style of posting. To evaluate our model, we collect over 20, 000 questions posted on Wenwo, a social Q&A application based on Weibo, along with all their responders. Our experimental results over the collected dataset demonstrate the effectiveness of responder prediction based on non-QA features and proposed potential implications for system design.

AB - Given the recent advancement of online social networking technologies, social question and answering has become an important venue for individuals to seek and share information. While studies have suggested the possibilities of routing questions to potential answerers for their help and the information provided, there is little analysis proposed to identify the characteristics that differentiate the possible responders from the nonresponders. In order to address such gap, in this work we present a model to predict potential responders in social Q&A using only non-QA-based attributes. We build the classifier using features from two different aspects, including: features extracted from one's social profile and style of posting. To evaluate our model, we collect over 20, 000 questions posted on Wenwo, a social Q&A application based on Weibo, along with all their responders. Our experimental results over the collected dataset demonstrate the effectiveness of responder prediction based on non-QA features and proposed potential implications for system design.

KW - Information seeking

KW - Social networks

KW - Social Q&A

KW - Social question and answering

KW - Social search

KW - Weibo

UR - http://www.scopus.com/inward/record.url?scp=84900531833&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900531833&partnerID=8YFLogxK

U2 - 10.1145/2559206.2581366

DO - 10.1145/2559206.2581366

M3 - Conference contribution

AN - SCOPUS:84900531833

SN - 9781450324748

SP - 2131

EP - 2136

BT - Conference on Human Factors in Computing Systems - Proceedings

PB - Association for Computing Machinery

ER -