User churn in focused question answering sites: Characterizations and prediction

Jagat Pudipeddi, Leman Akoglu, Hanghang Tong

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

19 Citations (Scopus)

Abstract

Given a user on a Q&A site, how can we tell whether s/he is engaged with the site or is rather likely to leave? What are the most evidential factors that relate to users churning? Question and Answer (Q&A) sites form excellent repos- itories of collective knowledge. To make these sites self- sustainable and long-lasting, it is crucial to ensure that new users as well as the site veterans who provide most of the answers keep engaged with the site. As such, quantifying the engagement of users and preventing churn in Q&A sites are vital to improve the lifespan of these sites. We study a large data collection from stackoverflow.com to identify significant factors that correlate with newcomer user churn in the early stage and those that relate to veterans leaving in the later stage. We consider the problem under two settings: given (i) the first k posts, or (ii) first T days of activity of a user, we aim to identify evidential features to automatically classify users so as to spot those who are about to leave. We find that in both cases, the time gap between subsequent posts is the most significant indicator of diminishing interest of users, besides other indicative factors like answering speed, reputation of those who answer their questions, and number of answers received by the user.

Original languageEnglish (US)
Title of host publicationWWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web
PublisherAssociation for Computing Machinery, Inc
Pages469-474
Number of pages6
ISBN (Electronic)9781450327459
DOIs
StatePublished - Apr 7 2014
Externally publishedYes
Event23rd International Conference on World Wide Web, WWW 2014 - Seoul, Korea, Republic of
Duration: Apr 7 2014Apr 11 2014

Other

Other23rd International Conference on World Wide Web, WWW 2014
CountryKorea, Republic of
CitySeoul
Period4/7/144/11/14

Keywords

  • Churn prediction
  • Feature extraction
  • Q and A sites
  • User churn

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Cite this

Pudipeddi, J., Akoglu, L., & Tong, H. (2014). User churn in focused question answering sites: Characterizations and prediction. In WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web (pp. 469-474). Association for Computing Machinery, Inc. https://doi.org/10.1145/2567948.2576965

User churn in focused question answering sites : Characterizations and prediction. / Pudipeddi, Jagat; Akoglu, Leman; Tong, Hanghang.

WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. Association for Computing Machinery, Inc, 2014. p. 469-474.

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

Pudipeddi, J, Akoglu, L & Tong, H 2014, User churn in focused question answering sites: Characterizations and prediction. in WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. Association for Computing Machinery, Inc, pp. 469-474, 23rd International Conference on World Wide Web, WWW 2014, Seoul, Korea, Republic of, 4/7/14. https://doi.org/10.1145/2567948.2576965
Pudipeddi J, Akoglu L, Tong H. User churn in focused question answering sites: Characterizations and prediction. In WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. Association for Computing Machinery, Inc. 2014. p. 469-474 https://doi.org/10.1145/2567948.2576965
Pudipeddi, Jagat ; Akoglu, Leman ; Tong, Hanghang. / User churn in focused question answering sites : Characterizations and prediction. WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. Association for Computing Machinery, Inc, 2014. pp. 469-474
@inproceedings{0db3a3573d4f498e9f3887d4968638e0,
title = "User churn in focused question answering sites: Characterizations and prediction",
abstract = "Given a user on a Q&A site, how can we tell whether s/he is engaged with the site or is rather likely to leave? What are the most evidential factors that relate to users churning? Question and Answer (Q&A) sites form excellent repos- itories of collective knowledge. To make these sites self- sustainable and long-lasting, it is crucial to ensure that new users as well as the site veterans who provide most of the answers keep engaged with the site. As such, quantifying the engagement of users and preventing churn in Q&A sites are vital to improve the lifespan of these sites. We study a large data collection from stackoverflow.com to identify significant factors that correlate with newcomer user churn in the early stage and those that relate to veterans leaving in the later stage. We consider the problem under two settings: given (i) the first k posts, or (ii) first T days of activity of a user, we aim to identify evidential features to automatically classify users so as to spot those who are about to leave. We find that in both cases, the time gap between subsequent posts is the most significant indicator of diminishing interest of users, besides other indicative factors like answering speed, reputation of those who answer their questions, and number of answers received by the user.",
keywords = "Churn prediction, Feature extraction, Q and A sites, User churn",
author = "Jagat Pudipeddi and Leman Akoglu and Hanghang Tong",
year = "2014",
month = "4",
day = "7",
doi = "10.1145/2567948.2576965",
language = "English (US)",
pages = "469--474",
booktitle = "WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - User churn in focused question answering sites

T2 - Characterizations and prediction

AU - Pudipeddi, Jagat

AU - Akoglu, Leman

AU - Tong, Hanghang

PY - 2014/4/7

Y1 - 2014/4/7

N2 - Given a user on a Q&A site, how can we tell whether s/he is engaged with the site or is rather likely to leave? What are the most evidential factors that relate to users churning? Question and Answer (Q&A) sites form excellent repos- itories of collective knowledge. To make these sites self- sustainable and long-lasting, it is crucial to ensure that new users as well as the site veterans who provide most of the answers keep engaged with the site. As such, quantifying the engagement of users and preventing churn in Q&A sites are vital to improve the lifespan of these sites. We study a large data collection from stackoverflow.com to identify significant factors that correlate with newcomer user churn in the early stage and those that relate to veterans leaving in the later stage. We consider the problem under two settings: given (i) the first k posts, or (ii) first T days of activity of a user, we aim to identify evidential features to automatically classify users so as to spot those who are about to leave. We find that in both cases, the time gap between subsequent posts is the most significant indicator of diminishing interest of users, besides other indicative factors like answering speed, reputation of those who answer their questions, and number of answers received by the user.

AB - Given a user on a Q&A site, how can we tell whether s/he is engaged with the site or is rather likely to leave? What are the most evidential factors that relate to users churning? Question and Answer (Q&A) sites form excellent repos- itories of collective knowledge. To make these sites self- sustainable and long-lasting, it is crucial to ensure that new users as well as the site veterans who provide most of the answers keep engaged with the site. As such, quantifying the engagement of users and preventing churn in Q&A sites are vital to improve the lifespan of these sites. We study a large data collection from stackoverflow.com to identify significant factors that correlate with newcomer user churn in the early stage and those that relate to veterans leaving in the later stage. We consider the problem under two settings: given (i) the first k posts, or (ii) first T days of activity of a user, we aim to identify evidential features to automatically classify users so as to spot those who are about to leave. We find that in both cases, the time gap between subsequent posts is the most significant indicator of diminishing interest of users, besides other indicative factors like answering speed, reputation of those who answer their questions, and number of answers received by the user.

KW - Churn prediction

KW - Feature extraction

KW - Q and A sites

KW - User churn

UR - http://www.scopus.com/inward/record.url?scp=84963536064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963536064&partnerID=8YFLogxK

U2 - 10.1145/2567948.2576965

DO - 10.1145/2567948.2576965

M3 - Conference contribution

AN - SCOPUS:84963536064

SP - 469

EP - 474

BT - WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web

PB - Association for Computing Machinery, Inc

ER -