skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: ColdRoute: effective routing of cold questions in stack exchange sites

Abstract

Routing questions in Community Question Answer services such as Stack Exchange sites is a well-studied problem. Yet, cold-start—a phenomena observed when a new question is posted is not well addressed by existing approaches. Additionally, cold questions posted by new askers present significant challenges to state-of-the-art approaches. We propose ColdRoute to address these challenges. ColdRoute is able to handle the task of routing cold questions posted by new or existing askers to matching experts. Specifically, we use Factorization Machines on the one-hot encoding of critical features such as question tags and compare our approach to well-studied techniques such as CQARank and semantic matching (LDA, BoW, and Doc2Vec). Furthermore by using data from eight stack exchange sites, we are able to improve upon the routing metrics (Precision@1, Accuracy, MRR) over the state-of-the-art models such as semantic matching by 159.5, 31.84, and 40.36% for cold questions posted by existing askers, and 123.1, 27.03, and 34.81% for cold questions posted by new askers respectively.

Authors:
ORCiD logo [1];  [2];  [3];  [2];  [1]
  1. The Ohio State Univ., Columbus, OH (United States)
  2. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
  3. Microsoft, Albuquerque, NM (United States)
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1460547
Grant/Contract Number:  
CCF-1645599; IIS-1550302; CNS-1513120; PAS0166; AC05-76RL01830
Resource Type:
Accepted Manuscript
Journal Name:
Data Mining and Knowledge Discovery
Additional Journal Information:
Journal Volume: 32; Journal Issue: 5; Journal ID: ISSN 1384-5810
Country of Publication:
United States
Language:
English
Subject:
96 KNOWLEDGE MANAGEMENT AND PRESERVATION; Question routing; Expert finding; Cold-start problem; Question answering services

Citation Formats

Sun, Jiankai, Vishnu, Abhinav, Chakrabarti, Aniket, Siegel, Charles, and Parthasarathy, Srinivasan. ColdRoute: effective routing of cold questions in stack exchange sites. United States: N. p., 2018. Web. doi:10.1007/s10618-018-0577-7.
Sun, Jiankai, Vishnu, Abhinav, Chakrabarti, Aniket, Siegel, Charles, & Parthasarathy, Srinivasan. ColdRoute: effective routing of cold questions in stack exchange sites. United States. doi:10.1007/s10618-018-0577-7.
Sun, Jiankai, Vishnu, Abhinav, Chakrabarti, Aniket, Siegel, Charles, and Parthasarathy, Srinivasan. Fri . "ColdRoute: effective routing of cold questions in stack exchange sites". United States. doi:10.1007/s10618-018-0577-7. https://www.osti.gov/servlets/purl/1460547.
@article{osti_1460547,
title = {ColdRoute: effective routing of cold questions in stack exchange sites},
author = {Sun, Jiankai and Vishnu, Abhinav and Chakrabarti, Aniket and Siegel, Charles and Parthasarathy, Srinivasan},
abstractNote = {Routing questions in Community Question Answer services such as Stack Exchange sites is a well-studied problem. Yet, cold-start—a phenomena observed when a new question is posted is not well addressed by existing approaches. Additionally, cold questions posted by new askers present significant challenges to state-of-the-art approaches. We propose ColdRoute to address these challenges. ColdRoute is able to handle the task of routing cold questions posted by new or existing askers to matching experts. Specifically, we use Factorization Machines on the one-hot encoding of critical features such as question tags and compare our approach to well-studied techniques such as CQARank and semantic matching (LDA, BoW, and Doc2Vec). Furthermore by using data from eight stack exchange sites, we are able to improve upon the routing metrics (Precision@1, Accuracy, MRR) over the state-of-the-art models such as semantic matching by 159.5, 31.84, and 40.36% for cold questions posted by existing askers, and 123.1, 27.03, and 34.81% for cold questions posted by new askers respectively.},
doi = {10.1007/s10618-018-0577-7},
journal = {Data Mining and Knowledge Discovery},
number = 5,
volume = 32,
place = {United States},
year = {2018},
month = {6}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 1 work
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Expert Finding for Question Answering via Graph Regularized Matrix Completion
journal, April 2015

  • Zhao, Zhou; Zhang, Lijun; He, Xiaofei
  • IEEE Transactions on Knowledge and Data Engineering, Vol. 27, Issue 4
  • DOI: 10.1109/TKDE.2014.2356461

Ranking user authority with relevant knowledge categories for expert finding
journal, April 2013


Social Recommendation with Cross-Domain Transferable Knowledge
journal, November 2015

  • Jiang, Meng; Cui, Peng; Chen, Xumin
  • IEEE Transactions on Knowledge and Data Engineering, Vol. 27, Issue 11
  • DOI: 10.1109/TKDE.2015.2432811

A Comprehensive Survey and Classification of Approaches for Community Question Answering
journal, August 2016

  • Srba, Ivan; Bielikova, Maria
  • ACM Transactions on the Web, Vol. 10, Issue 3
  • DOI: 10.1145/2934687

Factorization Machines with libFM
journal, May 2012

  • Rendle, Steffen
  • ACM Transactions on Intelligent Systems and Technology, Vol. 3, Issue 3
  • DOI: 10.1145/2168752.2168771

    Works referencing / citing this record:

    Ranking user authority with relevant knowledge categories for expert finding
    journal, April 2013


    Factorization Machines with libFM
    journal, May 2012

    • Rendle, Steffen
    • ACM Transactions on Intelligent Systems and Technology, Vol. 3, Issue 3
    • DOI: 10.1145/2168752.2168771

    A Comprehensive Survey and Classification of Approaches for Community Question Answering
    journal, August 2016

    • Srba, Ivan; Bielikova, Maria
    • ACM Transactions on the Web, Vol. 10, Issue 3
    • DOI: 10.1145/2934687