Predicting answering behaviour in online question answering communities

Grégoire Burel, Paul Mulholland, Yulan He, Harith Alani

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

Abstract

The value of Question Answering (Q&A) communities is dependent on members of the community finding the questions they are most willing and able to answer. This can be difficult in communities with a high volume of questions. Much previous has work attempted to address this problem by recommending questions similar to those already answered. However, this approach disregards the question selection behaviour of the answers and how it is affected by factors such as question recency and reputation. In this paper, we identify the parameters that correlate with such a behaviour by analysing the users' answering patterns in a Q&A community. We then generate a model to predict which question a user is most likely to answer next. We train Learning to Rank (LTR) models to predict question selections using various user, question and thread feature sets. We show that answering behaviour can be predicted with a high level of success, and highlight the particular features that inuence users' question selections.

Original languageEnglish
Title of host publicationHT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media
Place of PublicationNew York, NY (US)
PublisherACM
Pages201-210
Number of pages10
ISBN (Print)978-1-4503-3395-5
DOIs
Publication statusPublished - 24 Aug 2015
Event26th ACM Conference on Hypertext and Social Media - Guzelyurt, Cyprus
Duration: 1 Sep 20154 Sep 2015

Conference

Conference26th ACM Conference on Hypertext and Social Media
Abbreviated titleHT 2015
CountryCyprus
CityGuzelyurt
Period1/09/154/09/15

Keywords

  • online communities
  • social media
  • social Q&A platforms
  • user behaviour

Cite this

Burel, G., Mulholland, P., He, Y., & Alani, H. (2015). Predicting answering behaviour in online question answering communities. In HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media (pp. 201-210). New York, NY (US): ACM. https://doi.org/10.1145/2700171.2791041
Burel, Grégoire ; Mulholland, Paul ; He, Yulan ; Alani, Harith. / Predicting answering behaviour in online question answering communities. HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media. New York, NY (US) : ACM, 2015. pp. 201-210
@inproceedings{9e97ab81f61749bb9bf1ff160e875ebe,
title = "Predicting answering behaviour in online question answering communities",
abstract = "The value of Question Answering (Q&A) communities is dependent on members of the community finding the questions they are most willing and able to answer. This can be difficult in communities with a high volume of questions. Much previous has work attempted to address this problem by recommending questions similar to those already answered. However, this approach disregards the question selection behaviour of the answers and how it is affected by factors such as question recency and reputation. In this paper, we identify the parameters that correlate with such a behaviour by analysing the users' answering patterns in a Q&A community. We then generate a model to predict which question a user is most likely to answer next. We train Learning to Rank (LTR) models to predict question selections using various user, question and thread feature sets. We show that answering behaviour can be predicted with a high level of success, and highlight the particular features that inuence users' question selections.",
keywords = "online communities, social media, social Q&A platforms, user behaviour",
author = "Gr{\'e}goire Burel and Paul Mulholland and Yulan He and Harith Alani",
year = "2015",
month = "8",
day = "24",
doi = "10.1145/2700171.2791041",
language = "English",
isbn = "978-1-4503-3395-5",
pages = "201--210",
booktitle = "HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media",
publisher = "ACM",
address = "United States",

}

Burel, G, Mulholland, P, He, Y & Alani, H 2015, Predicting answering behaviour in online question answering communities. in HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media. ACM, New York, NY (US), pp. 201-210, 26th ACM Conference on Hypertext and Social Media, Guzelyurt, Cyprus, 1/09/15. https://doi.org/10.1145/2700171.2791041

Predicting answering behaviour in online question answering communities. / Burel, Grégoire; Mulholland, Paul; He, Yulan; Alani, Harith.

HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media. New York, NY (US) : ACM, 2015. p. 201-210.

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

TY - GEN

T1 - Predicting answering behaviour in online question answering communities

AU - Burel, Grégoire

AU - Mulholland, Paul

AU - He, Yulan

AU - Alani, Harith

PY - 2015/8/24

Y1 - 2015/8/24

N2 - The value of Question Answering (Q&A) communities is dependent on members of the community finding the questions they are most willing and able to answer. This can be difficult in communities with a high volume of questions. Much previous has work attempted to address this problem by recommending questions similar to those already answered. However, this approach disregards the question selection behaviour of the answers and how it is affected by factors such as question recency and reputation. In this paper, we identify the parameters that correlate with such a behaviour by analysing the users' answering patterns in a Q&A community. We then generate a model to predict which question a user is most likely to answer next. We train Learning to Rank (LTR) models to predict question selections using various user, question and thread feature sets. We show that answering behaviour can be predicted with a high level of success, and highlight the particular features that inuence users' question selections.

AB - The value of Question Answering (Q&A) communities is dependent on members of the community finding the questions they are most willing and able to answer. This can be difficult in communities with a high volume of questions. Much previous has work attempted to address this problem by recommending questions similar to those already answered. However, this approach disregards the question selection behaviour of the answers and how it is affected by factors such as question recency and reputation. In this paper, we identify the parameters that correlate with such a behaviour by analysing the users' answering patterns in a Q&A community. We then generate a model to predict which question a user is most likely to answer next. We train Learning to Rank (LTR) models to predict question selections using various user, question and thread feature sets. We show that answering behaviour can be predicted with a high level of success, and highlight the particular features that inuence users' question selections.

KW - online communities

KW - social media

KW - social Q&A platforms

KW - user behaviour

UR - http://www.scopus.com/inward/record.url?scp=84956970556&partnerID=8YFLogxK

U2 - 10.1145/2700171.2791041

DO - 10.1145/2700171.2791041

M3 - Conference contribution

AN - SCOPUS:84956970556

SN - 978-1-4503-3395-5

SP - 201

EP - 210

BT - HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media

PB - ACM

CY - New York, NY (US)

ER -

Burel G, Mulholland P, He Y, Alani H. Predicting answering behaviour in online question answering communities. In HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media. New York, NY (US): ACM. 2015. p. 201-210 https://doi.org/10.1145/2700171.2791041