skip to main content
10.1145/3358528.3358592acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicbdtConference Proceedingsconference-collections
research-article

Research on the Quality Prediction of Online Chinese Question Answering Community Answers Based on Comments

Published: 28 August 2019 Publication History

Abstract

With the rapid development of online Community Question Answer (CQA), a large volume of valuable data has been accumulated in CQA sites, as well as a huge number of low-quality answers. To improve the user-friendliness of CQA sites and help users find high-quality answers quickly, in this paper, we propose a supervised learning model to evaluate the quality of answers on Chinese CQA sites. We build a quality evaluation model based on the pairwise learning-to-rank algorithm and combine a set of features to rank answers according to their quality. In the quality evaluation process, we also propose an innovative type of feature named "the sentiment polarity of comments". Experimental results on real CQA data show that our method can efficiently produce a quality-ranking list of answers. Moreover, the proposed sentiment polarity feature can improve the performance of the quality evaluation model significantly.

References

[1]
M. AllahbakhshB, Benatallah, A. Ignjatovic, H.R. Motahari-Nezhad, E. Bertino, S.Dustdar, Quality control in crowdsouring systems: issues and directions[J], Internet Computing, IEEE 17 (2) (2013): 76--81.
[2]
Thorsten Joachims, Hang Li, Tie-Yan Liu, and ChengXiang Zhai. 2007. Learning to rank for information retrieval (LR4IR 2007). SIGIR Forum 41, 2 (December 2007), 58--62.
[3]
Thorsten Joachims. 2006. Training linear SVMs in linear time. In Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '06). ACM, New York, NY, USA, 217--226. DOI=http://dx.doi.org/10.1145/1150402.1150429.
[4]
Chris Burges, et al. Learning to Rank using Gradient Descent [C], ICML, ICML '05 Proceedings of the 22nd international conference on Machine learning. 2005:89--96.
[5]
Y. Freund, R. lyer, et al. A Efficient Boosting Algorithm for Combining Preferences[C], Proceedings ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning 2003:170--178.
[6]
Xu Anying, Ji Zongchen, Wang Bing. Answer Quality Prediction Based on the Answering Order in Community Question Answering [J]. Journal of Chinese Information Processing. 132--138, (2017) (in Chinese)
[7]
MengTao Sun, Lei Liu, Hao Chen. An Answer Quality Evaluation Algorithm Based on Semantic in Community Based Question Answering[C]. 2018 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). IEEE. 2018:971--978.
[8]
Qiaoling Liu, Eugene Agichtein, Gideon Dror, Evgeniy Gabrilovich, Yoelle Maarek, Dan Pelleg, and Idan Szpektor. 2011. Predicting web searcher satisfaction with existing community-based answers. In Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval (SIGIR '11). ACM, New York, NY, USA, 415--424. DOI=http://dx.doi.org/10.1145/2009916.2009974.
[9]
George Gkotsis, Karen Stepanyan, Carlos Pedrinaci, John Domingue, and Maria Liakata. 2014. It's all in the content: state of the art best answer prediction based on discretisation of shallow linguistic features. In Proceedings of the 2014 ACM conference on Web science (WebSci '14). ACM, New York, NY, USA, 202--210.
[10]
Ma Z, Sun A, Yuan Q, et al. A Tri-role topic model for domain-specific question answering [C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence.2015:224--230.
[11]
Wei Emma Zhang, Quan Z.Sheng, Zhejun Tang, Wenjie Ruan. Related or Duplicate: Distinguishing Similar CQA Questions via Convolutional Neural Networks. SIGIR'18, Ann, Arbor, MI, USA.2018:8--12.
[12]
YuFei Xie, ShuChun Liu, TangRen Yao, Zhao Lu. Focusing Attention Network for Answer Ranking. [C] Proceeding WWW'19 The World Wide Web Conference. 2019:3384--3390.
[13]
M.Surdeanu, M.Ciaramita, H. Zaragoza, Learning to rank answers to non-factoid questions from web collections, Computational Linguistics 37 (2) (2011):351--383.
[14]
E. Agichtein, C. Castillo, D. Donato, A. Gionis, G. Mishne, Finding high-quality content in social media, in: Proceedings of WSDM, 2008:183--194.
[15]
HengYi Fu, Sanghee Oh. Quality assessment of answers with user-identified criteria and data-driven features in social Q&A.[J]. Information Processing &Management. 2019:14--28.
[16]
Hapnes Toba, Zhao-Yan Ming, Mirna Adriani, Tat-seng Chua. Discovering high quality answers in community question answering archives using a hierarchy of classifiers[J]. Information Sciences 261 (2014):101--115.
[17]
Mohan John Blooma, Alton Y. K. Chua, and Dion Hoe-Lian Goh. 2008. A predictive framework for retrieving the best answer. In Proceedings of the 2008 ACM symposium on Applied computing (SAC '08). ACM, New York, NY, USA, 1107--1111.
[18]
Blei D M, Ng A Y, Jordan M I. Latent dirichlet allocation[J]. Journal of Machine Learning Research, 2003(3): 993--1022.
[19]
Griffiths T. Gibbs sampling in the generative model of latent dirichlet allocation[R]. Stanford: Stanford University, 2002.
[20]
Yuan Jian, Liu Yu. Answer quality evaluation model for community question answering based on hybrid method[J]. Application Research of Computer. 2017.34 (6):1708--1712. (In Chinese)
[21]
Han W W, Que X, Song S. Ranking potential reply-providers in community question answering system[J]. Communications, 2013, 10(10),125--136.

Cited By

View all
  • (2022)Feature Extraction to Filter Out Low-Quality Answers from Social Question Answering SitesIETE Journal of Research10.1080/03772063.2022.2048715(1-12)Online publication date: 21-Mar-2022
  • (2022)Predicting the quality of answers with less bias in online health question answering communitiesInformation Processing and Management: an International Journal10.1016/j.ipm.2022.10311259:6Online publication date: 1-Nov-2022
  • (2021)Evaluating and Predicting the Quality of Answers Factors in the Research Gate’s Question and Answer System: a Case Study of the Thematic Domain of Knowledge ManagementIranian Journal of Information Processing and Management10.52547/jipm.36.3.70936:3(709-736)Online publication date: 1-Apr-2021

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICBDT '19: Proceedings of the 2nd International Conference on Big Data Technologies
August 2019
382 pages
ISBN:9781450371926
DOI:10.1145/3358528
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

  • Shandong Univ.: Shandong University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 28 August 2019

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. CQA
  2. answer quality prediction
  3. community question answer
  4. ranking learning
  5. topic model

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Funding Sources

Conference

ICBDT2019

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)11
  • Downloads (Last 6 weeks)0
Reflects downloads up to 17 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2022)Feature Extraction to Filter Out Low-Quality Answers from Social Question Answering SitesIETE Journal of Research10.1080/03772063.2022.2048715(1-12)Online publication date: 21-Mar-2022
  • (2022)Predicting the quality of answers with less bias in online health question answering communitiesInformation Processing and Management: an International Journal10.1016/j.ipm.2022.10311259:6Online publication date: 1-Nov-2022
  • (2021)Evaluating and Predicting the Quality of Answers Factors in the Research Gate’s Question and Answer System: a Case Study of the Thematic Domain of Knowledge ManagementIranian Journal of Information Processing and Management10.52547/jipm.36.3.70936:3(709-736)Online publication date: 1-Apr-2021

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media