Abstract

There are users who generate significant amounts of domain knowledge in online forums or community question and answer (CQA) websites. Existing literature defines them as 'experts.' These users attain such statuses by providing multiple relevant answers to the question askers. Past works have focused on recommending relevant posts to these users. With the rise of web forums where certified experts answer questions, strategies that are tailored towards addressing the new type of experts will be beneficial. In this paper, we identify a new type of user called 'designated experts' (i.e., users designated as domain experts by the web administrators). These are the experts who are guaranteed by web administrators to be an expert in a given domain. Our focus is on how we can capture the unique behavior of designated experts in an online domain. We have noticed designated experts have different behaviors compared to CQA experts. In particular, unlike existing CQAs, only one designated expert responds to any given thread. To capture this intuition, we introduce a matrix factorization algorithm with regularization to capture the behavior. Our results show that the regularization method improves the performance significantly compared to the baseline approach.

Original languageEnglish (US)
Pages659-666
Number of pages8
DOIs
StatePublished - 2015
EventIEEE: Big Data - Santa Clara, United States
Duration: Oct 29 2015Nov 1 2015

Conference

ConferenceIEEE
CountryUnited States
CitySanta Clara
Period10/29/1511/1/15

Fingerprint

Factorization
Websites

Keywords

  • Designated Experts
  • Matrix factorization
  • Online Forums
  • Recommender Systems

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Software

Cite this

Cho, J. H. D., Li, Y., Girju, R., & Zhai, C. (2015). Recommending forum posts to designated experts. 659-666. Paper presented at IEEE, Santa Clara, United States. https://doi.org/10.1109/BigData.2015.7363810

Recommending forum posts to designated experts. / Cho, Jason H D; Li, Yanen; Girju, Roxana; Zhai, Chengxiang.

2015. 659-666 Paper presented at IEEE, Santa Clara, United States.

Research output: Contribution to conferencePaper

Cho, JHD, Li, Y, Girju, R & Zhai, C 2015, 'Recommending forum posts to designated experts' Paper presented at IEEE, Santa Clara, United States, 10/29/15 - 11/1/15, pp. 659-666. https://doi.org/10.1109/BigData.2015.7363810
Cho JHD, Li Y, Girju R, Zhai C. Recommending forum posts to designated experts. 2015. Paper presented at IEEE, Santa Clara, United States. https://doi.org/10.1109/BigData.2015.7363810
Cho, Jason H D ; Li, Yanen ; Girju, Roxana ; Zhai, Chengxiang. / Recommending forum posts to designated experts. Paper presented at IEEE, Santa Clara, United States.8 p.
@conference{ae60597e9fc44b849a67b683a5c538cc,
title = "Recommending forum posts to designated experts",
abstract = "There are users who generate significant amounts of domain knowledge in online forums or community question and answer (CQA) websites. Existing literature defines them as 'experts.' These users attain such statuses by providing multiple relevant answers to the question askers. Past works have focused on recommending relevant posts to these users. With the rise of web forums where certified experts answer questions, strategies that are tailored towards addressing the new type of experts will be beneficial. In this paper, we identify a new type of user called 'designated experts' (i.e., users designated as domain experts by the web administrators). These are the experts who are guaranteed by web administrators to be an expert in a given domain. Our focus is on how we can capture the unique behavior of designated experts in an online domain. We have noticed designated experts have different behaviors compared to CQA experts. In particular, unlike existing CQAs, only one designated expert responds to any given thread. To capture this intuition, we introduce a matrix factorization algorithm with regularization to capture the behavior. Our results show that the regularization method improves the performance significantly compared to the baseline approach.",
keywords = "Designated Experts, Matrix factorization, Online Forums, Recommender Systems",
author = "Cho, {Jason H D} and Yanen Li and Roxana Girju and Chengxiang Zhai",
year = "2015",
doi = "10.1109/BigData.2015.7363810",
language = "English (US)",
pages = "659--666",
note = "IEEE : Big Data ; Conference date: 29-10-2015 Through 01-11-2015",

}

TY - CONF

T1 - Recommending forum posts to designated experts

AU - Cho, Jason H D

AU - Li, Yanen

AU - Girju, Roxana

AU - Zhai, Chengxiang

PY - 2015

Y1 - 2015

N2 - There are users who generate significant amounts of domain knowledge in online forums or community question and answer (CQA) websites. Existing literature defines them as 'experts.' These users attain such statuses by providing multiple relevant answers to the question askers. Past works have focused on recommending relevant posts to these users. With the rise of web forums where certified experts answer questions, strategies that are tailored towards addressing the new type of experts will be beneficial. In this paper, we identify a new type of user called 'designated experts' (i.e., users designated as domain experts by the web administrators). These are the experts who are guaranteed by web administrators to be an expert in a given domain. Our focus is on how we can capture the unique behavior of designated experts in an online domain. We have noticed designated experts have different behaviors compared to CQA experts. In particular, unlike existing CQAs, only one designated expert responds to any given thread. To capture this intuition, we introduce a matrix factorization algorithm with regularization to capture the behavior. Our results show that the regularization method improves the performance significantly compared to the baseline approach.

AB - There are users who generate significant amounts of domain knowledge in online forums or community question and answer (CQA) websites. Existing literature defines them as 'experts.' These users attain such statuses by providing multiple relevant answers to the question askers. Past works have focused on recommending relevant posts to these users. With the rise of web forums where certified experts answer questions, strategies that are tailored towards addressing the new type of experts will be beneficial. In this paper, we identify a new type of user called 'designated experts' (i.e., users designated as domain experts by the web administrators). These are the experts who are guaranteed by web administrators to be an expert in a given domain. Our focus is on how we can capture the unique behavior of designated experts in an online domain. We have noticed designated experts have different behaviors compared to CQA experts. In particular, unlike existing CQAs, only one designated expert responds to any given thread. To capture this intuition, we introduce a matrix factorization algorithm with regularization to capture the behavior. Our results show that the regularization method improves the performance significantly compared to the baseline approach.

KW - Designated Experts

KW - Matrix factorization

KW - Online Forums

KW - Recommender Systems

UR - http://www.scopus.com/inward/record.url?scp=84963783287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963783287&partnerID=8YFLogxK

U2 - 10.1109/BigData.2015.7363810

DO - 10.1109/BigData.2015.7363810

M3 - Paper

AN - SCOPUS:84963783287

SP - 659

EP - 666

ER -