Predicting closed questions on community question answering sites using convolutional neural network


Community questions answering sites receive a huge number of questions and answers everyday. It has been observed that a number of questions among them are marked as closed by the site moderators. Such questions increase overhead of the moderators and also create user dissatisfaction. This paper aims to predict whether a newly posted question would be marked as closed in the future or not and also give a tentative reason of being closed. Two models: (1) a baseline model based on traditional machine learning techniques and (2) deep learning models such as convolutional neural network (CNN) and long short-term memory (LSTM) network are used to classify a question into one of the five classes: (1) open, (2) off-topic, (3) not a real question, (4) too constructive and (5) too localized. The baseline model requires the handcrafted features and hence does not preserve semantics. However, CNN and LSTM networks are capable of preserving the semantics of question’s word and extracting the hidden features from the textual content using multiple hidden layers. The LSTM network performs better compared to CNN and traditional machine learning models. The proposed model can be used as an initial filter to screen the closed question at the time of posting, which reduced the overheads of site moderators. To the best of our knowledge, this is the first work that predicts the closed question along with the reason the question will be closed. This helps the questioner to modify the question before posting. The experimental results with the dataset of Stack Overflow prove the effectiveness of the proposed model.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23


  1. 1.

    Master question is the question that has similar content to the new question.

  2. 2.

    The greatest integer that is less than or equal to the value x.


  1. 1.

    Agichtein E, Castillo C, Donato D, Gionis A, Mishne G (2008) Finding high-quality content in social media. In: Proceedings of the 2008 international conference on web search and data mining. ACM, pp 183–194

  2. 2.

    Roy PK, Ahmad Z, Singh JP, Alryalat MAA, Rana NP, Dwivedi YK (2018) Finding and ranking high-quality answers in community question answering sites. Glob J Flex Syst Manag 19:53–68

    Article  Google Scholar 

  3. 3.

    ClosedQuestion (2018) Accessed 16 Feb 2018

  4. 4.

    Correa D, Sureka A (2013) Fit or unfit: analysis and prediction of ‘closed questions’ on stack overflow. In: Proceedings of the first ACM conference on Online social networks. ACM, pp 201–212

  5. 5.

    Ahasanuzzaman M, Asaduzzaman M, Roy C K, Schneider KA (2016) Mining duplicate questions of stack overflow. In: 2016 IEEE/ACM 13th working conference on mining software repositories (MSR). IEEE, pp 402–412

  6. 6.

    Zhang Y, Lo D, Xia X, Sun J-L (2015) Multi-factor duplicate question detection in stack overflow. J Comput Sci Technol 30(5):981–997

    Article  Google Scholar 

  7. 7.

    Zhang WE, Sheng QZ, Lau JH, Abebe E, Ruan W (2018) Duplicate detection in programming question answering communities. ACM Trans Internet Technol (TOIT) 18(3):37

    Google Scholar 

  8. 8.

    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

  9. 9.

    Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  10. 10.

    Jeon J, Croft W B, Lee JH, Park S (2006) A framework to predict the quality of answers with non-textual features. In: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval. ACM, pp 228–235

  11. 11.

    Blooma MJ, Chua AY, Goh DH-L (2008) A predictive framework for retrieving the best answer. In: Proceedings of the 2008 ACM symposium on applied computing. ACM, pp 1107–1111

  12. 12.

    Toba H, Ming Z-Y, Adriani M, Chua T-S (2014) Discovering high quality answers in community question answering archives using a hierarchy of classifiers. Inf Sci 261:101–115

    MathSciNet  Article  Google Scholar 

  13. 13.

    Wu H, Tian Z, Wu W, Chen E (2017) An unsupervised approach for low-quality answer detection in community question-answering. In: International conference on database systems for advanced applications. Springer, pp 85–101

  14. 14.

    Lee CT, Rodrigues EM, Kazai G, Milic-Frayling N, Ignjatovic A (2009) Model for voter scoring and best answer selection in community Q&A services. In: IEEE/WIC/ACM international joint conferences on web intelligence and intelligent agent technologies, 2009. WI-IAT’09, vol 1. IEEE, pp 116–123

  15. 15.

    Shah C, Pomerantz J (2010) Evaluating and predicting answer quality in community QA. In: Proceedings of the 33rd international ACM SIGIR conference on research and development in information retrieval. ACM, pp 411–418

  16. 16.

    Zhu Z, Bernhard D, Gurevych I (2009) A multi-dimensional model for assessing the quality of answers in social Q&A sites. PhD thesis

  17. 17.

    Blooma MJ, Chua AY-K, Goh DH-L (2010) Selection of the best answer in CQA services. In: 2010 Seventh international conference on information technology: new generations (ITNG). IEEE, pp 534–539

  18. 18.

    Srba I, Bielikova M (2016) Why is stack overflow failing? Preserving sustainability in community question answering. IEEE Softw 33(4):80–89

    Article  Google Scholar 

  19. 19.

    Correa D, Sureka A (2014) Chaff from the wheat: characterization and modeling of deleted questions on stack overflow. In: Proceedings of the 23rd international conference on world wide web. ACM, pp 631–642

  20. 20.

    Ponzanelli L, Mocci A, Bacchelli A, Lanza M, Fullerton D (2014) Improving low quality stack overflow post detection. In: 2014 IEEE international conference on software maintenance and evolution (ICSME). IEEE, pp 541–544

  21. 21.

    Zhang WE, Sheng QZ, Shu Y, Nguyen VK (2017) Feature analysis for duplicate detection in programming QA communities. In: International conference on advanced data mining and applications. Springer, pp 623–638

  22. 22.

    Mizobuchi Y, Takayama K (2017) Two improvements to detect duplicates in stack overflow. In: 2017 IEEE 24th international conference on software analysis, evolution and reengineering (SANER). IEEE, pp 563–564

  23. 23.

    Zhang WE, Sheng QZ, Lau JH, Abebe E (2017) Detecting duplicate posts in programming QA communities via latent semantics and association rules. In: Proceedings of the 26th international conference on world wide web. International World Wide Web Conferences Steering Committee, pp 1221–1229

  24. 24.

    Hoogeveen D, Bennett A, Li Y, Verspoor KM, Baldwin T (2018) Detecting misflagged duplicate questions in community question-answering archives. In: Twelfth international AAAI conference on web and social media, pp 112–120

  25. 25.

    Liang D, Zhang F, Zhang W, Zhang Q, Fu J, Peng M, Gui T, Huang X (2019) Adaptive multi-attention network incorporating answer information for duplicate question detection. In: Proceedings of the 42Nd international ACM SIGIR conference on research and development in information retrieval, SIGIR’19, New York, NY, USA. ACM, pp 95–104

  26. 26.

    Abric D, Clark OE, Caminiti M, Gallaba K, McIntosh S (2019) Can duplicate questions on stack overflow benefit the software development community? In: Proceedings of the 16th international conference on mining software repositories. IEEE Press, pp 230–234

  27. 27.

    Yang L, Bao S, Lin Q, Wu X, Han D, Su Z, Yu Y (2011) Analyzing and predicting not-answered questions in community-based question answering services. In: AAAI, vol 11, pp 1273–1278

  28. 28.

    Dror G, Maarek Y, Szpektor I (2013) Will my question be answered? Predicting “question answerability” in community question-answering sites. In: ECML/PKDD, vol 3, pp499–514

  29. 29.

    Asaduzzaman M, Mashiyat AS, Roy CK, Schneider KA (2013) Answering questions about unanswered questions of stack overflow. In: 2013 10th IEEE working conference on mining software repositories (MSR). IEEE, pp 97–100

  30. 30.

    Liu J, Shen H, Yu L (2017) Question quality analysis and prediction in community question answering services with coupled mutual reinforcement. IEEE Trans Serv Comput 10(2):286–301

    Article  Google Scholar 

  31. 31.

    Xia X, Lo D, Correa D, Sureka A, Shihab E (2016) It takes two to tango: deleted stack overflow question prediction with text and meta features. In: 2016 IEEE 40th annual computer software and applications conference (COMPSAC), vol 1. IEEE, pp 73–82

  32. 32.

    Rish I (2001) An empirical study of the naive Bayes classifier. In: IJCAI 2001 workshop on empirical methods in artificial intelligence, vol 3. IBM, pp 41–46

  33. 33.

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

    MathSciNet  Article  Google Scholar 

  34. 34.

    Liaw A, Wiener M et al (2002) Classification and regression by randomforest. R News 2(3):18–22

    Google Scholar 

  35. 35.

    Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27

    Article  Google Scholar 

  36. 36.

    Yin Z, Kong D, Shao G, Ning X, Jin W, Wang JY (2016) A-optimal convolutional neural network. Neural Comput Appl 30(7):2295–2304

    Article  Google Scholar 

  37. 37.

    Becherer N, Pecarina J, Nykl S, Hopkinson K (2017) Improving optimization of convolutional neural networks through parameter fine-tuning. Neural Comput Appl 31(8):3469–3479

    Article  Google Scholar 

  38. 38.

    Singh JP, Irani S, Rana NP, Dwivedi YK, Saumya S, Roy PK (2017) Predicting the “helpfulness” of online consumer reviews. J Bus Res 70:346–355

    Article  Google Scholar 

  39. 39.

    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436

    Article  Google Scholar 

  40. 40.

    Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Empirical methods in natural language processing (EMNLP), pp 1532–1543

  41. 41.

    Severyn A, Moschitti A (2015) Learning to rank short text pairs with convolutional deep neural networks. In: Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval. ACM, pp 373–382

  42. 42.

    Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853

  43. 43.

    Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa P (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493–2537

    MATH  Google Scholar 

  44. 44.

    Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747

  45. 45.

    Pascanu R, Gulcehre C, Cho K, Bengio Y (2013) How to construct deep recurrent neural networks. arXiv preprint arXiv:1312.6026

  46. 46.

    Jiang K, Feng S, Song Q, Calix RA, Gupta M, Bernard GR (2018) Identifying tweets of personal health experience through word embedding and LSTM neural network. BMC Bioinform 19(8):210

    Article  Google Scholar 

  47. 47.

    Lee JY, Dernoncourt F (2016) Sequential short-text classification with recurrent and convolutional neural networks. arXiv preprint arXiv:1603.03827

  48. 48.

    Zhou C, Sun C, Liu Z, Lau F (2015) A C-LSTM neural network for text classification. arXiv preprint arXiv:1511.08630

  49. 49.

    Hua Y, Zhao Z, Li R, Chen X, Liu Z, Zhang H (2019) Deep learning with long short-term memory for time series prediction. IEEE Commun Mag 57:114–119

    Article  Google Scholar 

  50. 50.

    Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 315–323

  51. 51.

    Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357

    Article  Google Scholar 

  52. 52.

    Chall JS, Dale E (1995) Manual for use of the new Dale-Chall readability formula. Brookline Books, Brookline

    Google Scholar 

  53. 53.

    Kincaid JP, Fishburne RP Jr, Rogers RL, Chissom BS (1975) Derivation of new readability formulas (automated readability index, fog count and Flesch reading ease formula) for navy enlisted personnel. Technical report, DTIC Document

Download references

Author information



Corresponding author

Correspondence to Pradeep Kumar Roy.

Additional information

Publisher's Note

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

Appendix: List of extracted textual features with their description

Appendix: List of extracted textual features with their description

See Fig. 24 and Table 21.

Fig. 24

Convolutional neural network model architecture created using Keras

Table 21 List of selected features with their description on stack overflow dataset

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Roy, P.K., Singh, J.P. Predicting closed questions on community question answering sites using convolutional neural network. Neural Comput & Applic 32, 10555–10572 (2020).

Download citation


  • Community question answering
  • Closed questions
  • CNN
  • LSTM