Skip to main content

Expert finding in community question answering: a review

Abstract

The rapid development of Community Question Answering (CQA) satisfies users’ quest for professional and personal knowledge about anything. In CQA, one central issue is to find users with expertise and willingness to answer the given questions. Expert finding in CQA often exhibits very different challenges compared to traditional methods. The new features of CQA (such as huge volume, sparse data and crowdsourcing) violate fundamental assumptions of traditional recommendation systems. This paper focuses on reviewing and categorizing the current progress on expert finding in CQA. We classify the recent solutions into four different categories: matrix factorization based models (MF-based models), gradient boosting tree based models (GBT-based models), deep learning based models (DL-based models) and ranking based models (R-based models). We find that MF-based models outperform other categories of models in the crowdsourcing situation. Moreover, we use innovative diagrams to clarify several important concepts of ensemble learning, and find that ensemble models with several specific single models can further boost the performance. Further, we compare the performance of different models on different types of matching tasks, including textvs.text, graphvs.text, audiovs.text and videovs.text. The results will help the model selection of expert finding in practice. Finally, we explore some potential future issues in expert finding research in CQA.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Notes

  1. https://www.quora.com/What-percentage-of-questions-on-Quora-have-no-answers.

  2. https://biendata.com/competition/bytecup2016/.

  3. http://answers.google.com.

  4. https://www.quora.com/.

  5. https://answers.yahoo.com/.

  6. https://stackoverflow.com/.

  7. http://www.answers.com/.

  8. https://www.zhihu.com/.

  9. https://www.wukong.com/.

  10. https://zhidao.baidu.com/.

  11. https://wenwen.sogou.com/.

  12. More details of experiment results will be clarified in Sect. 10.

  13. https://grouplens.org/datasets/movielens/1m/.

  14. https://biendata.com/competition/luckydata/.

  15. https://www.kaggle.com/c/data-science-bowl-2017.

  16. https://www.kaggle.com/c/mlsp-2013-birds.

  17. https://www.kaggle.com/c/youtube8m.

  18. http://ms-multimedia-challenge.com/2016/challenge.

  19. Its accuracy is larger than 0.5.

References

  • Adomavicius G, Tuzhilin A (2005) Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans Knowl Data Eng 6:734–749

    Article  Google Scholar 

  • Alarfaj F, Kruschwitz U, Hunter D, Fox C (2012) Finding the right supervisor: expert-finding in a university domain. In: Association for Computational Linguistics, pp 1–6

  • Balog K, Fang Y, De Rijke M, Serdyukov P, Si L (2012) Expertise retrieval. Found Trends Inf Retr 6(23):127–256

    Article  Google Scholar 

  • Beutel A, Chi EH, Cheng Z, Pham H, Anderson J (2017) Beyond globally optimal: focused learning for improved recommendations. In: International conference on world wide web, pp 203–212

  • Beutel A, Covington P, Jain S, Xu C, Li J, Gatto V, Chi EH (2018) Latent cross: making use of context in recurrent recommender systems. In: International conference on web search and data mining, pp 46–54

  • Bifet A, Holmes G, Pfahringer B, Kirkby R, Gavaldà R (2009) New ensemble methods for evolving data streams. In: International conference on knowledge discovery and data mining, pp 139–148

  • Boeva V, Angelova M, Tsiporkova E (2017) Data-driven techniques for expert finding. In: International conference on agents and artificial intelligence, pp 535–542

  • Bordes A, Chopra S, Weston J (2014) Question answering with subgraph embeddings. arXiv preprint arXiv:1406.3676

  • Bouguessa M, Wang S (2008) Identifying authoritative actors in question-answering forums: the case of yahoo! answers. In: International conference on knowledge discovery and data mining, pp 866–874

  • Bozzon A, Brambilla M, Ceri S, Silvestri M, Vesci G (2013) Choosing the right crowd: expert finding in social networks. In: International conference on extending database technology, pp 637–648

  • Breiman L (1996) Bagging predictors. Mach Learn 26(2):123–140

    MATH  Google Scholar 

  • Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: International conference on knowledge discovery and data mining, pp 785–794

  • Chen T, Zhang W, Lu Q, Chen K, Zheng Z, Yu Y (2012) SVDFeature: a toolkit for feature-based collaborative filtering. J Mach Learn Res 13:3619–3622

    MathSciNet  MATH  Google Scholar 

  • Cheng X, Zhu S, Chen G, Su S (2015) Exploiting user feedback for expert finding in community question answering. In: International conference on data mining, pp 295–302

  • Cheng HT, Koc L, Harmsen J, Shaked T, Chandra T, Aradhye H, Anderson G, Corrado G, Chai W, Ispir M et al (2016) Wide and deep learning for recommender systems. In: Workshop on deep learning for recommender systems, pp 7–10

  • Christakopoulou E, Karypis G (2016) Local item-item models for top-n recommendation. In: ACM conference on recommender systems, pp 67–74

  • Covington P, Adams J, Sargin E (2016) Deep neural networks for youtube recommendations. In: Conference on recommender systems, pp 191–198

  • Dai H, Wang Y, Trivedi R, Song L (2016) Recurrent coevolutionary latent feature processes for continuous-time recommendation. In: Recsys workshop on deep learning for recommendation systems, pp 29–34

  • Dargahi Nobari A, Sotudeh Gharebagh S, Neshati M (2017) Skill translation models in expert finding. In: International ACM SIGIR conference on research and development in information retrieval, pp 1057–1060

  • Daud A, Li J, Zhou L, Muhammad F (2010) Temporal expert finding through generalized time topic modeling. Knowl Based Syst 23(6):615–625

    Article  Google Scholar 

  • Deng H, King I, Lyu MR (2009) Formal models for expert finding on dblp bibliography data. In: International conference on data mining, pp 163–172

  • Ebesu T, Shen B, Fang Y (2018) Collaborative memory network for recommendation systems. In: International ACM SIGIR conference on research and development in information retrieval

  • Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232

    MathSciNet  MATH  Article  Google Scholar 

  • Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28(2):337–374

    MathSciNet  MATH  Article  Google Scholar 

  • Gunawardana A, Shani G (2009) A survey of accuracy evaluation metrics of recommendation tasks. J Mach Learn Res 10(12):2935–2962

    MathSciNet  MATH  Google Scholar 

  • Han F, Tan S, Sun H, Srivatsa M, Cai D, Yan X (2016) Distributed representations of expertise. In: International conference on data mining, pp 531–539

  • Hashemi SH, Neshati M, Beigy H (2013) Expertise retrieval in bibliographic network: a topic dominance learning approach. In: International conference on information and knowledge management, pp 1117–1126

  • He X, Liao L, Zhang H, Nie L, Hu X, Chua TS (2017) Neural collaborative filtering. In: International conference on world wide web, pp 173–182

  • Hidasi B, Karatzoglou A, Baltrunas L, Tikk D (2015) Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939

  • Hu Y, Koren Y, Volinsky C (2008) Collaborative filtering for implicit feedback datasets. In: ieee international conference on data mining, pp 263–272

  • Jing H, Smola AJ (2017) Neural survival recommender. In: International conference on web search and data mining, pp 515–524

  • Joachims T (2006) Training linear SVMS in linear time. In: International conference on knowledge discovery and data mining, pp 217–226

  • Johnson RW (2001) An introduction to the bootstrap. Teach Stat 23(2):49C54

    MathSciNet  Article  Google Scholar 

  • Karimzadehgan M, White RW, Richardson M (2009) Enhancing expert finding using organizational hierarchies. In: European conference on information retrieval, pp 177–188

    Google Scholar 

  • Kawale J, Fu Y (2015) Deep collaborative filtering via marginalized denoising auto-encoder. In: International on conference on information and knowledge management, pp 811–820

  • Kingma DP, Ba J (2014) A method for stochastic optimization. In: International conference on learning representations, pp 1–15

  • Koren Y (2008) Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: International conference on knowledge discovery and data mining, pp 426–434

  • Koren Y, Bell R, Volinsky C et al (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30–37

    Article  Google Scholar 

  • Lee J, Kim S, Lebanon G, Singer Y (2013) Local low-rank matrix approximation. In: International conference on machine learning, pp 82–90

  • Li Q, Zheng X (2017) Deep collaborative autoencoder for recommender systems: a unified framework for explicit and implicit feedback. arXiv preprint arXiv:1712.09043

  • Li X, Ma J, Yang Y, Wang D (2013) A service mode of expert finding in social network. In: International conference on service sciences, pp 220–223

  • Li H, Jin S, Shudong L (2015a) A hybrid model for experts finding in community question answering. In: International conference on cyber-enabled distributed computing and knowledge discovery, pp 176–185

  • Li X, Liu Y, Zhang M, Ma S, Zhu X, Sun J (2015b) Detecting promotion campaigns in community question answering. In: International joint conference on artificial intelligence, pp 2348–2354

  • Li Y, Ma S, Huang R (2015c) Social context analysis for topic-specific expert finding in online learning communities. Smart Learn Environ 5(1):57–74

    Google Scholar 

  • Liang S, de Rijke M (2016) Formal language models for finding groups of experts. Inf Process Manag 52(4):529–549

    Article  Google Scholar 

  • Lin L, Xu Z, Ding Y, Liu X (2013) Finding topic-level experts in scholarly networks. Scientometrics 97(3):797–819

    Article  Google Scholar 

  • Lin S, Hong W, Wang D, Li T (2017) A survey on expert finding techniques. J Intell Inf Syst 49(2):255–279

    Article  Google Scholar 

  • Linden G, Smith B, York J (2003) Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Comput 7(1):76–80

    Article  Google Scholar 

  • Liu X, Koll M, Koll M (2005) Finding experts in community-based question-answering services. In: International conference on information and knowledge management, pp 315–316

  • Liu J, Song YI, Lin CY (2011) Competition-based user expertise score estimation. In: ACM SIGIR conference on research and development in information retrieval, pp 425–434

  • Liu DR, Chen YH, Kao WC, Wang HW (2013a) Integrating expert profile, reputation and link analysis for expert finding in question-answering websites. Inf Process Manag 49(1):312–329

    Article  Google Scholar 

  • Liu J, Qi LI, Liu B, Zhang Y (2013b) An expert finding method based on topic model. J Natl Univ Def Technol 35(2):127–131

    Google Scholar 

  • Liu X, Ye S, Li X, Luo Y, Rao Y (2015) Zhihurank: a topic-sensitive expert finding algorithm in community question answering websites. In: International conference on web based learning, pp 165–173

    Chapter  Google Scholar 

  • Mimno D, Mccallum A (2007) Expertise modeling for matching papers with reviewers. In: International conference on knowledge discovery and data mining, pp 500–509

  • Momtazi S, Naumann F (2013) Topic modeling for expert finding using latent Dirichlet allocation. Wiley Interdiscip Rev Data Min Knowl Discov 3(5):346C353

    Article  Google Scholar 

  • Neshati M, Fallahnejad Z, Beigy H (2017) On dynamicity of expert finding in community question answering. Inf Process Manag 53(5):1026–1042

    Article  Google Scholar 

  • Paatero P, Tapper U (1994) Positive matrix factorization: a nonnegative factor model with optimal utilization of error estimates of data values. Environmetrics 5(2):111–126

    Article  Google Scholar 

  • Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: International conference on knowledge discovery and data mining, pp 701–710

  • Pezzotti N, Lelieveldt B, Maaten LVD, Hollt T, Eisemann E, Vilanova A (2017) Approximated and user steerable tsne for progressive visual analytics. IEEE Trans Vis Comput Graph 23(7):1739–1752

    Article  Google Scholar 

  • Qian Y, Tang J, Wu K (2018) Weakly learning to match experts in online community. In: International joint conference on artificial intelligence, pp 3841–3847

  • Qiu X, Huang X (2015) Convolutional neural tensor network architecture for community-based question answering. In: International joint conference on artificial intelligence, pp 1305–1311

  • Rani SK, Raju K, Kumari VV (2015) Expert finding system using latent effort ranking in academic social networks. Int J Inf Technol Comput Sci 7(2):21–27

    Google Scholar 

  • Rendle S (2011) Factorization machines. In: International conference on data mining, pp 995–1000

  • Rendle S (2012) Factorization machines with libfm. Trans Intell Syst Technol 3(57):1–22

    Google Scholar 

  • Riahi F, Zolaktaf Z, Shafiei M, Milios E (2012) Finding expert users in community question answering. In: International conference on world wide web, pp 791–798

  • Salakhutdinov R, Mnih A, Hinton G (2007) Restricted Boltzmann machines for collaborative filtering. In: International conference on machine learning, pp 791–798

  • Sedhain S, Menon AK, Sanner S, Xie L (2015) Autorec: autoencoders meet collaborative filtering. In: International conference on world wide web, pp 111–112

  • Tan YK, Xu X, Liu Y (2016) Improved recurrent neural networks for session-based recommendations. In: Workshop on deep learning for recommender systems, pp 17–22

  • Vincent P, Larochelle H, Bengio Y, Manzagol P (2008) Extracting and composing robust features with denoising autoencoders. In: International conference on machine learning, p 1096–1103

  • Wan S, Lan Y, Guo J, Xu J, Pang L, Cheng X (2016) Match-srnn: modeling the recursive matching structure with spatial rnn. In: International joint conference on artificial intelligence, pp 2922–2928

  • Wang GA, Jiao J, Abrahams AS, Fan W, Zhang Z (2013) Expertrank: a topic-aware expert finding algorithm for online knowledge communities. Decis Support Syst 54(3):1442–1451

    Article  Google Scholar 

  • Wei J, He J, Chen K, Zhou Y, Tang Z (2017) Collaborative filtering and deep learning based recommendation system for cold start items. Expert Syst Appl 69:29–39

    Article  Google Scholar 

  • Wu Y, DuBois C, Zheng AX, Ester M (2016) Collaborative denoising auto-encoders for top-n recommender systems. In: ACM international conference on web search and data mining, pp 153–162

  • Wu CY, Ahmed A, Beutel A, Smola AJ, Jing H (2017) Recurrent recommender networks. In: International conference on web search and data mining, pp 495–503

  • Yang L, Qiu M, Gottipati S, Zhu F, Jiang J (2013) Cqarank: jointly model topics and expertise in community question answering. In: International conference on information and knowledge management, pp 99–108

  • Yeniterzi R, Callan J (2014) Constructing effective and efficient topic-specific authority networks for expert finding in social media. In: International workshop on social media retrieval and analysis, pp 45–50

  • Ying H, Chen L, Xiong Y, Wu J (2016) Collaborative deep ranking: a hybrid pair-wise recommendation algorithm with implicit feedback. In: Pacific-asia conference on knowledge discovery and data mining, pp 555–567

    Chapter  Google Scholar 

  • Zhang S, Yao L, Xu X (2017) Autosvd++: an efficient hybrid collaborative filtering model via contractive auto-encoders. In: SIGIR conference on research and development in information retrieval, pp 957–960

  • Zhao T, Bian N, Li C, Li M (2013) Topic-level expert modeling in community question answering. In: International conference on data mining, pp 776–784

  • Zhao Z, Wei F, Zhou M, Ng W (2015a) Cold-start expert finding in community question answering via graph regularization. In: International conference on database systems for advanced applications, pp 21–38

    Chapter  Google Scholar 

  • Zhao Z, Zhang L, He X, Ng W (2015b) Expert finding for question answering via graph regularized matrix completion. IEEE Trans Knowl Data Eng 27(4):993–1004

    Article  Google Scholar 

  • Zhao Z, Yang Q, Cai D, He X, Zhuang Y (2016) Expert finding for community-based question answering via ranking metric network learning. In: International joint conference on artificial intelligence, pp 3000–3006

  • Zheng Y, Tang B, Ding W, Zhou H (2016) A neural autoregressive approach to collaborative filtering. arXiv preprint arXiv:1605.09477

  • Zhou G, Lai S, Liu K, Zhao J (2012) Topic-sensitive probabilistic model for expert finding in question answer communities. In: International conference on information and knowledge management, pp 1662–1666

  • Zhou G, Zhao J, He T, Wu W (2014) An empirical study of topic-sensitive probabilistic model for expert finding in question answer communities. Knowl Based Syst 66(9):136–145

    Article  Google Scholar 

  • Zhu H, Chen E, Xiong H, Cao H, Tian J (2014) Ranking user authority with relevant knowledge categories for expert finding. World Wide Web 17(5):1081–1107

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by the NSFC for Distinguished Young Scholar (61825602), National Natural Science Foundation of China (61806111), and the National High Technology Research and Development Program of China (863 Program) (2015AA124102).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jie Tang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Yuan, S., Zhang, Y., Tang, J. et al. Expert finding in community question answering: a review. Artif Intell Rev 53, 843–874 (2020). https://doi.org/10.1007/s10462-018-09680-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-018-09680-6

Keywords

  • Expert finding
  • Matrix factorization
  • Deep learning
  • Ensemble learning