{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T16:24:41Z","timestamp":1758817481498,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T00:00:00Z","timestamp":1593388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Cyber Security Cooperative Research Centre"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,29]]},"DOI":"10.1145\/3379597.3387443","type":"proceedings-article","created":{"date-parts":[[2020,9,19]],"date-time":"2020-09-19T02:12:49Z","timestamp":1600481569000},"page":"350-361","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["PUMiner"],"prefix":"10.1145","author":[{"given":"Triet Huynh Minh","family":"Le","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Hin","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, Australia and Cyber Security Cooperative Research Centre"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Croft","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Ali","family":"Babar","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, Australia and Cyber Security Cooperative Research Centre"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,9,18]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Security breaches in 2019. Retrieved 1\/12\/2019 from https:\/\/us.norton.com\/internetsecurity-emerging-threats-2019-data-breaches.html. Security breaches in 2019. Retrieved 1\/12\/2019 from https:\/\/us.norton.com\/internetsecurity-emerging-threats-2019-data-breaches.html."},{"key":"e_1_3_2_1_2_1","unstructured":"Common Vulnerabilities and Exposures. Retrieved 1\/12\/2019 from https:\/\/cve.mitre.org\/. Common Vulnerabilities and Exposures. Retrieved 1\/12\/2019 from https:\/\/cve.mitre.org\/."},{"key":"e_1_3_2_1_3_1","unstructured":"National Vulnerability Database. Retrieved 1\/12\/2019 from https:\/\/nvd.nist.gov\/. National Vulnerability Database. Retrieved 1\/12\/2019 from https:\/\/nvd.nist.gov\/."},{"key":"e_1_3_2_1_4_1","unstructured":"Common Weakness Enumeration. Retrieved 1\/12\/2019 from https:\/\/cwe.mitre.org\/. Common Weakness Enumeration. Retrieved 1\/12\/2019 from https:\/\/cwe.mitre.org\/."},{"key":"e_1_3_2_1_5_1","unstructured":"Common Attack Pattern Enumeration and Classification. Retrieved 1\/12\/2019 from https:\/\/capec.mitre.org\/. Common Attack Pattern Enumeration and Classification. Retrieved 1\/12\/2019 from https:\/\/capec.mitre.org\/."},{"key":"e_1_3_2_1_6_1","unstructured":"Open Web Application Security Project Retrieved 1\/12\/2019 from https:\/\/www.owasp.org\/index.php\/Main_Page. Open Web Application Security Project Retrieved 1\/12\/2019 from https:\/\/www.owasp.org\/index.php\/Main_Page."},{"key":"e_1_3_2_1_7_1","unstructured":"SQL injection mitigations in CWE. Retrieved 1\/12\/2019 from https:\/\/cwe.mitre.org\/data\/definitions\/89.html#oc_89_Potential_Mitigations. SQL injection mitigations in CWE. Retrieved 1\/12\/2019 from https:\/\/cwe.mitre.org\/data\/definitions\/89.html#oc_89_Potential_Mitigations."},{"key":"e_1_3_2_1_8_1","unstructured":"Deprecation of mysql_real_escape_string(). Retrieved 1\/12\/2019 from https:\/\/www.php.net\/manual\/en\/intro.mysql.php. Deprecation of mysql_real_escape_string(). Retrieved 1\/12\/2019 from https:\/\/www.php.net\/manual\/en\/intro.mysql.php."},{"key":"e_1_3_2_1_9_1","unstructured":"Discussion on SQL injection mitigations on Stack Overflow. Retrieved 1\/12\/2019 from https:\/\/stackoverflow.com\/questions\/60174\/how-can-i-prevent-sql-injection-in-php. Discussion on SQL injection mitigations on Stack Overflow. Retrieved 1\/12\/2019 from https:\/\/stackoverflow.com\/questions\/60174\/how-can-i-prevent-sql-injection-in-php."},{"key":"e_1_3_2_1_10_1","unstructured":"Stack Overflow. Retrieved 1\/12\/2019 from https:\/\/stackoverflow.com\/. Stack Overflow. Retrieved 1\/12\/2019 from https:\/\/stackoverflow.com\/."},{"key":"e_1_3_2_1_11_1","volume-title":"An empirical case study on Stack Overflow to explore developers' security challenges","author":"Rahman M. S.","year":"2016","unstructured":"Rahman , M. S. 2016. An empirical case study on Stack Overflow to explore developers' security challenges ( 2016 ). Rahman, M. S. 2016. An empirical case study on Stack Overflow to explore developers' security challenges (2016)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-016-1672-0"},{"volume-title":"Proceedings of the 51st Hawaii International Conference on System Sciences.","author":"Zahedi M.","key":"e_1_3_2_1_13_1","unstructured":"Zahedi , M. , Ali Babar , M. and Treude , C . 2018. An empirical study of security issues posted in open source projects . In Proceedings of the 51st Hawaii International Conference on System Sciences. Zahedi, M., Ali Babar, M. and Treude, C. 2018. An empirical study of security issues posted in open source projects. In Proceedings of the 51st Hawaii International Conference on System Sciences."},{"volume-title":"Proceedings of the 11th Working Conference on Mining Software Repositories","author":"Pletea D.","key":"e_1_3_2_1_14_1","unstructured":"Pletea , D. , Vasilescu , B. and Serebrenik , A . 2014. Security and emotion: sentiment analysis of security discussions on GitHub . In Proceedings of the 11th Working Conference on Mining Software Repositories , Hyderabad, India. ACM, 348--351. Pletea, D., Vasilescu, B. and Serebrenik, A. 2014. Security and emotion: sentiment analysis of security discussions on GitHub. In Proceedings of the 11th Working Conference on Mining Software Repositories, Hyderabad, India. ACM, 348--351."},{"volume-title":"Proceedings of the 16th International Conference on Mining Software Repositories","author":"Le T. H. M.","key":"e_1_3_2_1_15_1","unstructured":"Le , T. H. M. , Sabir , B. and Babar , M. A . 2019. Automated software vulnerability assessment with concept drift . In Proceedings of the 16th International Conference on Mining Software Repositories , Montreal, Quebec, Canada. IEEE Press, 371--382. Le, T. H. M., Sabir, B. and Babar, M. A. 2019. Automated software vulnerability assessment with concept drift. In Proceedings of the 16th International Conference on Mining Software Repositories, Montreal, Quebec, Canada. IEEE Press, 371--382."},{"volume-title":"Proceedings of Advances in Neural Information Processing Systems, 3111--3119","author":"Mikolov T.","key":"e_1_3_2_1_16_1","unstructured":"Mikolov , T. , Sutskever , I. , Chen , K. , Corrado , G. S. and Dean , J . 2013. Distributed representations of words and phrases and their compositionality . In Proceedings of Advances in Neural Information Processing Systems, 3111--3119 . Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S. and Dean, J. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of Advances in Neural Information Processing Systems, 3111--3119."},{"volume-title":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 1532--1543","author":"Pennington J.","key":"e_1_3_2_1_17_1","unstructured":"Pennington , J. , Socher , R. and Manning , C . 2014. Glove: Global vectors for word representation . In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 1532--1543 . Pennington, J., Socher, R. and Manning, C. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 1532--1543."},{"volume-title":"Proceedings of the 15th International Conference on Mining Software Repositories","author":"Efstathiou V.","key":"e_1_3_2_1_18_1","unstructured":"Efstathiou , V. , Chatzilenas , C. and Spinellis , D . 2018. Word embeddings for the software engineering domain . In Proceedings of the 15th International Conference on Mining Software Repositories , Gothenburg, Sweden. ACM, 38--41. Efstathiou, V., Chatzilenas, C. and Spinellis, D. 2018. Word embeddings for the software engineering domain. In Proceedings of the 15th International Conference on Mining Software Repositories, Gothenburg, Sweden. ACM, 38--41."},{"volume-title":"Proceedings of International Conference on Machine Learning, 1188--1196","author":"Le Q.","key":"e_1_3_2_1_19_1","unstructured":"Le , Q. and Mikolov , T . 2014. Distributed representations of sentences and documents . In Proceedings of International Conference on Machine Learning, 1188--1196 . Le, Q. and Mikolov, T. 2014. Distributed representations of sentences and documents. In Proceedings of International Conference on Machine Learning, 1188--1196."},{"key":"e_1_3_2_1_20_1","unstructured":"Han J. Pei J. and Kamber M. 2011. Data mining: concepts and techniques. Elsevier. Han J. Pei J. and Kamber M. 2011. Data mining: concepts and techniques. Elsevier."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Friedman J. Hastie T. and Tibshirani R. 2001. The elements of statistical learning. Springer series in statistics New York. Friedman J. Hastie T. and Tibshirani R. 2001. The elements of statistical learning. Springer series in statistics New York.","DOI":"10.1007\/978-0-387-21606-5"},{"key":"e_1_3_2_1_22_1","unstructured":"Security StackExchange. Retrieved 1\/12\/2019 from https:\/\/security.stackexchange.com\/. Security StackExchange. Retrieved 1\/12\/2019 from https:\/\/security.stackexchange.com\/."},{"volume-title":"Proceedings of Advances in neural information processing systems, 582--588","author":"Sch\u00f6lkopf B.","key":"e_1_3_2_1_23_1","unstructured":"Sch\u00f6lkopf , B. , Williamson , R. C. , Smola , A. J. , Shawe-Taylor , J. and Platt , J. C . 2000. Support vector method for novelty detection . In Proceedings of Advances in neural information processing systems, 582--588 . Sch\u00f6lkopf, B., Williamson, R. C., Smola, A. J., Shawe-Taylor, J. and Platt, J. C. 2000. Support vector method for novelty detection. In Proceedings of Advances in neural information processing systems, 582--588."},{"volume-title":"Proceedings of 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), 396--401","author":"Mendsaikhan O.","key":"e_1_3_2_1_24_1","unstructured":"Mendsaikhan , O. , Hasegawa , H. , Yamaguchi , Y. and Shimada , H . 2019. Identification of cybersecurity specific content using the doc2vec language model . In Proceedings of 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), 396--401 . Mendsaikhan, O., Hasegawa, H., Yamaguchi, Y. and Shimada, H. 2019. Identification of cybersecurity specific content using the doc2vec language model. In Proceedings of 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), 396--401."},{"key":"e_1_3_2_1_25_1","unstructured":"Reproduction package. Retrieved 2\/3\/2020 from https:\/\/github.com\/lhmtriet\/PUMiner_MSR. Reproduction package. Retrieved 2\/3\/2020 from https:\/\/github.com\/lhmtriet\/PUMiner_MSR."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-012-9231-y"},{"key":"e_1_3_2_1_27_1","unstructured":"Database schema of Stack Overflow. Retrieved 1\/12\/2019 from https:\/\/data.stackexchange.com\/stackoverflow\/query\/new. Database schema of Stack Overflow. Retrieved 1\/12\/2019 from https:\/\/data.stackexchange.com\/stackoverflow\/query\/new."},{"volume-title":"Sampling techniques","author":"Cochran W. G.","key":"e_1_3_2_1_28_1","unstructured":"Cochran , W. G. 2007. Sampling techniques . John Wiley & Sons . Cochran, W. G. 2007. Sampling techniques. John Wiley & Sons."},{"volume-title":"Machine learning: a probabilistic perspective","author":"Murphy K. P.","key":"e_1_3_2_1_29_1","unstructured":"Murphy , K. P. 2012. Machine learning: a probabilistic perspective . MIT press . Murphy, K. P. 2012. Machine learning: a probabilistic perspective. MIT press."},{"key":"e_1_3_2_1_30_1","unstructured":"Bekker J. and Davis J. 2018. Learning from positive and unlabeled data: A survey. arXiv preprint arXiv:1811.04820 (2018). Bekker J. and Davis J. 2018. Learning from positive and unlabeled data: A survey. arXiv preprint arXiv:1811.04820 (2018)."},{"key":"e_1_3_2_1_31_1","unstructured":"Dam H. K. Tran T. Pham T. T. M. Ng S. W. Grundy J. and Ghose A. 2018. Automatic feature learning for predicting vulnerable software components. IEEE Trans. Softw. Eng. (2018). Dam H. K. Tran T. Pham T. T. M. Ng S. W. Grundy J. and Ghose A. 2018. Automatic feature learning for predicting vulnerable software components. IEEE Trans. Softw. Eng. (2018)."},{"volume-title":"Proceedings of the 16th International Conference on Mining Software Repositories","author":"Hoang T.","key":"e_1_3_2_1_32_1","unstructured":"Hoang , T. , Dam , H. K. , Kamei , Y. , Lo , D. and Ubayashi , N . 2019. DeepJIT: an end-to-end deep learning framework for just-in-time defect prediction . In Proceedings of the 16th International Conference on Mining Software Repositories , Montreal, Quebec, Canada. IEEE Press, 34--45. Hoang, T., Dam, H. K., Kamei, Y., Lo, D. and Ubayashi, N. 2019. DeepJIT: an end-to-end deep learning framework for just-in-time defect prediction. In Proceedings of the 16th International Conference on Mining Software Repositories, Montreal, Quebec, Canada. IEEE Press, 34--45."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Kao A. and Poteet S. R. 2007. Natural language processing and text mining. Springer Science & Business Media. Kao A. and Poteet S. R. 2007. Natural language processing and text mining. Springer Science & Business Media.","DOI":"10.1007\/978-1-84628-754-1"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1108\/eb046814"},{"volume-title":"Proceedings of 2017 IEEE International Conference on Software Maintenance and Evolution (ICSME), 125--136","author":"Han Z.","key":"e_1_3_2_1_35_1","unstructured":"Han , Z. , Li , X. , Xing , Z. , Liu , H. and Feng , Z . 2017. Learning to predict severity of software vulnerability using only vulnerability description . In Proceedings of 2017 IEEE International Conference on Software Maintenance and Evolution (ICSME), 125--136 . Han, Z., Li, X., Xing, Z., Liu, H. and Feng, Z. 2017. Learning to predict severity of software vulnerability using only vulnerability description. In Proceedings of 2017 IEEE International Conference on Software Maintenance and Evolution (ICSME), 125--136."},{"volume-title":"Proceedings of the 12th Working Conference on Mining Software Repositories","author":"White M.","key":"e_1_3_2_1_36_1","unstructured":"White , M. , Vendome , C. , Linares-V\u00e1squez , M. and Poshyvanyk , D . 2015. Toward deep learning software repositories . In Proceedings of the 12th Working Conference on Mining Software Repositories , Florence, Italy. IEEE Press, 334--345. White, M., Vendome, C., Linares-V\u00e1squez, M. and Poshyvanyk, D. 2015. Toward deep learning software repositories. In Proceedings of the 12th Working Conference on Mining Software Repositories, Florence, Italy. IEEE Press, 334--345."},{"volume-title":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 213--220","author":"Elkan C.","key":"e_1_3_2_1_37_1","unstructured":"Elkan , C. and Noto , K . 2008. Learning classifiers from only positive and unlabeled data . In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 213--220 . Elkan, C. and Noto, K. 2008. Learning classifiers from only positive and unlabeled data. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 213--220."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.06.010"},{"key":"e_1_3_2_1_39_1","unstructured":"Li X. and Liu B. 2003. Learning to classify texts using positive and unlabeled data. In IJCAI 587--592. Li X. and Liu B. 2003. Learning to classify texts using positive and unlabeled data. In IJCAI 587--592."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2014.11.001"},{"key":"e_1_3_2_1_41_1","unstructured":"Google BigQuery. Retrieved 1\/12\/2019 from https:\/\/cloud.google.com\/bigquery\/. Google BigQuery. Retrieved 1\/12\/2019 from https:\/\/cloud.google.com\/bigquery\/."},{"key":"e_1_3_2_1_42_1","unstructured":"Security StackExchange queries. Retrieved 1\/12\/2019 from https:\/\/data.stackexchange.com\/security\/queries. Security StackExchange queries. Retrieved 1\/12\/2019 from https:\/\/data.stackexchange.com\/security\/queries."},{"key":"e_1_3_2_1_43_1","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","author":"Pedregosa F.","year":"2011","unstructured":"Pedregosa , F. , Varoquaux , G. , Gramfort , A. , Michel , V. , Thirion , B. , Grisel , O. , Blondel , M. , Prettenhofer , P. , Weiss , R. and Dubourg , V. 2011 . Scikit-learn: Machine learning in Python . J. Mach. Learn. Res., 12 , Oct (2011), 2825 -- 2830 . Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R. and Dubourg, V. 2011. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res., 12, Oct (2011), 2825--2830.","journal-title":"J. Mach. Learn. Res., 12"},{"volume-title":"ACL 2004 on Interactive Poster and Demonstration Sessions. Association for Computational Linguistics, 31","author":"Bird S.","key":"e_1_3_2_1_44_1","unstructured":"Bird , S. and Loper , E . 2004. NLTK: the natural language toolkit . In ACL 2004 on Interactive Poster and Demonstration Sessions. Association for Computational Linguistics, 31 . Bird, S. and Loper, E. 2004. NLTK: the natural language toolkit. In ACL 2004 on Interactive Poster and Demonstration Sessions. Association for Computational Linguistics, 31."},{"volume-title":"Proceedings of LREC 2010 Workshop on New Challenges for NLP Frameworks. Citeseer.","author":"Rehurek R.","key":"e_1_3_2_1_45_1","unstructured":"Rehurek , R. and Sojka , P . 2010. Software framework for topic modelling with large corpora . In Proceedings of LREC 2010 Workshop on New Challenges for NLP Frameworks. Citeseer. Rehurek, R. and Sojka, P. 2010. Software framework for topic modelling with large corpora. In Proceedings of LREC 2010 Workshop on New Challenges for NLP Frameworks. Citeseer."},{"volume-title":"Proceedings of the 15th International Conference on Mining Software Repositories","author":"Majumder S.","key":"e_1_3_2_1_46_1","unstructured":"Majumder , S. , Balaji , N. , Brey , K. , Fu , W. and Menzies , T . 2018. 500+ times faster than deep learning: a case study exploring faster methods for text mining stackoverflow . In Proceedings of the 15th International Conference on Mining Software Repositories , Gothenburg, Sweden. ACM, 554--563. Majumder, S., Balaji, N., Brey, K., Fu, W. and Menzies, T. 2018. 500+ times faster than deep learning: a case study exploring faster methods for text mining stackoverflow. In Proceedings of the 15th International Conference on Mining Software Repositories, Gothenburg, Sweden. ACM, 554--563."},{"volume-title":"Proceedings of the 15th International Conference on Mining Software Repositories","author":"Ma Y.","key":"e_1_3_2_1_47_1","unstructured":"Ma , Y. , Fakhoury , S. , Christensen , M. , Arnaoudova , V. , Zogaan , W. and Mirakhorli , M . 2018. Automatic classification of software artifacts in open-source applications . In Proceedings of the 15th International Conference on Mining Software Repositories , Gothenburg, Sweden. ACM, 414--425. Ma, Y., Fakhoury, S., Christensen, M., Arnaoudova, V., Zogaan, W. and Mirakhorli, M. 2018. Automatic classification of software artifacts in open-source applications. In Proceedings of the 15th International Conference on Mining Software Repositories, Gothenburg, Sweden. ACM, 414--425."},{"key":"e_1_3_2_1_48_1","unstructured":"Kaggle. Retrieved 1\/12\/2019 from https:\/\/www.kaggle.com\/. Kaggle. Retrieved 1\/12\/2019 from https:\/\/www.kaggle.com\/."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/54.1-2.167"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/00031305.1992.10475879","article-title":"An introduction to kernel and nearest-neighbor nonparametric regression","volume":"46","author":"Altman N. S.","year":"1992","unstructured":"Altman , N. S. 1992 . An introduction to kernel and nearest-neighbor nonparametric regression . Am. Stat. , 46 , 3 (1992), 175 -- 185 . Altman, N. S. 1992. An introduction to kernel and nearest-neighbor nonparametric regression. Am. Stat., 46, 3 (1992), 175--185.","journal-title":"Am. Stat."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 3rd International Conference on Document Analysis and Recognition. IEEE, 278--282","author":"Ho T. K.","year":"1995","unstructured":"Ho , T. K. 1995 . Random decision forests . In Proceedings of the 3rd International Conference on Document Analysis and Recognition. IEEE, 278--282 . Ho, T. K. 1995. Random decision forests. In Proceedings of the 3rd International Conference on Document Analysis and Recognition. IEEE, 278--282."},{"volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 785--794","author":"Chen T.","key":"e_1_3_2_1_53_1","unstructured":"Chen , T. and Guestrin , C . 2016. Xgboost: A scalable tree boosting system . In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 785--794 . Chen, T. and Guestrin, C. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 785--794."},{"key":"e_1_3_2_1_54_1","volume-title":"-Y","author":"Ke G.","year":"2017","unstructured":"Ke , G. , Meng , Q. , Finley , T. , Wang , T. , Chen , W. , Ma , W. , Ye , Q. and Liu , T . -Y . 2017 . Lightgbm : A highly efficient gradient boosting decision tree. In Proceedings of Advances in Neural Information Processing Systems , 3146--3154. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q. and Liu, T.-Y. 2017. Lightgbm: A highly efficient gradient boosting decision tree. In Proceedings of Advances in Neural Information Processing Systems, 3146--3154."},{"key":"e_1_3_2_1_55_1","unstructured":"Lee W. S. and Liu B. 2003. Learning with positive and unlabeled examples using weighted logistic regression. In ICML 448--455. Lee W. S. and Liu B. 2003. Learning with positive and unlabeled examples using weighted logistic regression. In ICML 448--455."},{"volume-title":"Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 84--95","author":"Treude C.","key":"e_1_3_2_1_56_1","unstructured":"Treude , C. and Wagner , M . 2019. Predicting good configurations for GitHub and stack overflow topic models . In Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 84--95 . Treude, C. and Wagner, M. 2019. Predicting good configurations for GitHub and stack overflow topic models. In Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 84--95."},{"key":"e_1_3_2_1_57_1","unstructured":"Tantithamthavorn C. McIntosh S. Hassan A. E. and Matsumoto K. 2018. The impact of automated parameter optimization on defect prediction models. IEEE Trans. Softw. Eng. (2018). Tantithamthavorn C. McIntosh S. Hassan A. E. and Matsumoto K. 2018. The impact of automated parameter optimization on defect prediction models. IEEE Trans. Softw. Eng. (2018)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Mann H. B. and Whitney D. R. 1947. On a test of whether one of two random variables is stochastically larger than the other. Annals of mathematical statistics (1947) 50--60. Mann H. B. and Whitney D. R. 1947. On a test of whether one of two random variables is stochastically larger than the other. Annals of mathematical statistics (1947) 50--60.","DOI":"10.1214\/aoms\/1177730491"},{"key":"e_1_3_2_1_59_1","first-page":"139","article-title":"One-class SVMs for document classification","author":"Manevitz L. M.","year":"2001","unstructured":"Manevitz , L. M. and Yousef , M. 2001 . One-class SVMs for document classification . J. Mach. Learn. Res., 2 , Dec (2001), 139 -- 154 . Manevitz, L. M. and Yousef, M. 2001. One-class SVMs for document classification. J. Mach. Learn. Res., 2, Dec (2001), 139--154.","journal-title":"J. Mach. Learn. Res., 2"},{"key":"e_1_3_2_1_60_1","unstructured":"Stack Exchange sites. Retrieved 1\/12\/2019 from https:\/\/stackexchange.com\/sites. Stack Exchange sites. Retrieved 1\/12\/2019 from https:\/\/stackexchange.com\/sites."},{"volume-title":"Proceedings of the 16th International Conference on Mining Software Repositories","author":"Wang S.","key":"e_1_3_2_1_61_1","unstructured":"Wang , S. , Phan , N. , Wang , Y. and Zhao , Y . 2019. Extracting API tips from developer question and answer websites . In Proceedings of the 16th International Conference on Mining Software Repositories , Montreal, Quebec, Canada. IEEE Press, 321--332. Wang, S., Phan, N., Wang, Y. and Zhao, Y. 2019. Extracting API tips from developer question and answer websites. In Proceedings of the 16th International Conference on Mining Software Repositories, Montreal, Quebec, Canada. IEEE Press, 321--332."},{"volume-title":"Proceedings of the 38th IEEE\/ACM International Conference on Software Engineering (ICSE). IEEE, 392--403","author":"Treude C.","key":"e_1_3_2_1_62_1","unstructured":"Treude , C. and Robillard , M. P . 2016. Augmenting api documentation with insights from stack overflow . In Proceedings of the 38th IEEE\/ACM International Conference on Software Engineering (ICSE). IEEE, 392--403 . Treude, C. and Robillard, M. P. 2016. Augmenting api documentation with insights from stack overflow. In Proceedings of the 38th IEEE\/ACM International Conference on Software Engineering (ICSE). IEEE, 392--403."},{"volume-title":"Proceedings of the 38th International Conference on Software Engineering","author":"Ye X.","key":"e_1_3_2_1_63_1","unstructured":"Ye , X. , Shen , H. , Ma , X. , Bunescu , R. and Liu , C . 2016. From word embeddings to document similarities for improved information retrieval in software engineering . In Proceedings of the 38th International Conference on Software Engineering , Austin, Texas. Association for Computing Machinery, 404--415. Ye, X., Shen, H., Ma, X., Bunescu, R. and Liu, C. 2016. From word embeddings to document similarities for improved information retrieval in software engineering. In Proceedings of the 38th International Conference on Software Engineering, Austin, Texas. Association for Computing Machinery, 404--415."},{"volume-title":"Proceedings of the 28th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 562--567","author":"Wong E.","key":"e_1_3_2_1_64_1","unstructured":"Wong , E. , Yang , J. and Tan , L . 2013. Autocomment: Mining question and answer sites for automatic comment generation . In Proceedings of the 28th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 562--567 . Wong, E., Yang, J. and Tan, L. 2013. Autocomment: Mining question and answer sites for automatic comment generation. In Proceedings of the 28th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 562--567."},{"volume-title":"Proceedings of the 26th Annual International Conference on Computer Science and Software Engineering. IBM Corp., 232--242","author":"Campos E. C.","key":"e_1_3_2_1_65_1","unstructured":"Campos , E. C. , Monperrus , M. and Maia , M. A . 2016. Searching stack overflow for API-usage-related bug fixes using snippet-based queries . In Proceedings of the 26th Annual International Conference on Computer Science and Software Engineering. IBM Corp., 232--242 . Campos, E. C., Monperrus, M. and Maia, M. A. 2016. Searching stack overflow for API-usage-related bug fixes using snippet-based queries. In Proceedings of the 26th Annual International Conference on Computer Science and Software Engineering. IBM Corp., 232--242."},{"volume-title":"Proceedings of 2019 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM). IEEE, 1--12","author":"Thiselton E.","key":"e_1_3_2_1_66_1","unstructured":"Thiselton , E. and Treude , C . 2019. Enhancing Python compiler error messages via Stack Overflow . In Proceedings of 2019 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM). IEEE, 1--12 . Thiselton, E. and Treude, C. 2019. Enhancing Python compiler error messages via Stack Overflow. In Proceedings of 2019 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM). IEEE, 1--12."},{"key":"e_1_3_2_1_67_1","unstructured":"Ragkhitwetsagul C. Krinke J. Paixao M. Bianco G. and Oliveto R. 2019. Toxic code snippets on stack overflow. IEEE Trans. Softw. Eng. (2019). Ragkhitwetsagul C. Krinke J. Paixao M. Bianco G. and Oliveto R. 2019. Toxic code snippets on stack overflow. IEEE Trans. Softw. Eng. (2019)."},{"volume-title":"Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 240--244","author":"Nishi M. A.","key":"e_1_3_2_1_68_1","unstructured":"Nishi , M. A. , Ciborowska , A. and Damevski , K . 2019. Characterizing duplicate code snippets between stack overflow and tutorials . In Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 240--244 . Nishi, M. A., Ciborowska, A. and Damevski, K. 2019. Characterizing duplicate code snippets between stack overflow and tutorials. In Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 240--244."},{"volume-title":"Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 260--264","author":"Bangash A. A.","key":"e_1_3_2_1_69_1","unstructured":"Bangash , A. A. , Sahar , H. , Chowdhury , S. , Wong , A. W. , Hindle , A. and Ali , K . 2019. What do developers know about machine learning: a study of ML discussions on StackOverflow . In Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 260--264 . Bangash, A. A., Sahar, H., Chowdhury, S., Wong, A. W., Hindle, A. and Ali, K. 2019. What do developers know about machine learning: a study of ML discussions on StackOverflow. In Proceedings of the 16th International Conference on Mining Software Repositories. IEEE Press, 260--264."},{"volume-title":"Proceedings of the 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 432--442","author":"Bagherzadeh M.","key":"e_1_3_2_1_70_1","unstructured":"Bagherzadeh , M. and Khatchadourian , R . 2019. Going big: a large-scale study on what big data developers ask . In Proceedings of the 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 432--442 . Bagherzadeh, M. and Khatchadourian, R. 2019. Going big: a large-scale study on what big data developers ask. In Proceedings of the 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 432--442."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-015-9379-3"},{"key":"e_1_3_2_1_72_1","first-page":"993","article-title":"Latent dirichlet allocation","author":"Blei D. M.","year":"2003","unstructured":"Blei , D. M. , Ng , A. Y. and Jordan , M. I. 2003 . Latent dirichlet allocation . J. Mach. Learn. Res., 3 , Jan (2003), 993 -- 1022 . Blei, D. M., Ng, A. Y. and Jordan, M. I. 2003. Latent dirichlet allocation. J. Mach. Learn. Res., 3, Jan (2003), 993--1022.","journal-title":"J. Mach. Learn. Res., 3"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-017-9533-1"},{"volume-title":"Proceedings of 2014 IEEE International Conference on Software Maintenance and Evolution, 291--300","author":"Wang S.","key":"e_1_3_2_1_74_1","unstructured":"Wang , S. , Lo , D. , Vasilescu , B. and Serebrenik , A . 2014. EnTagRec: An Enhanced Tag Recommendation System for Software Information Sites . In Proceedings of 2014 IEEE International Conference on Software Maintenance and Evolution, 291--300 . Wang, S., Lo, D., Vasilescu, B. and Serebrenik, A. 2014. EnTagRec: An Enhanced Tag Recommendation System for Software Information Sites. In Proceedings of 2014 IEEE International Conference on Software Maintenance and Evolution, 291--300."},{"volume-title":"Proceedings of the 10th Working Conference on Mining Software Repositories (MSR). IEEE, 287--296","author":"Xia X.","key":"e_1_3_2_1_75_1","unstructured":"Xia , X. , Lo , D. , Wang , X. and Zhou , B . 2013. Tag recommendation in software information sites . In Proceedings of the 10th Working Conference on Mining Software Repositories (MSR). IEEE, 287--296 . Xia, X., Lo, D., Wang, X. and Zhou, B. 2013. Tag recommendation in software information sites. In Proceedings of the 10th Working Conference on Mining Software Repositories (MSR). IEEE, 287--296."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3092566"},{"volume-title":"Proceedings of the 34th International Conference on Software Engineering (ICSE), 771--781","author":"Shahzad M.","key":"e_1_3_2_1_77_1","unstructured":"Shahzad , M. , Shafiq , M. Z. and Liu , A. X . 2012. A large scale exploratory analysis of software vulnerability life cycles . In Proceedings of the 34th International Conference on Software Engineering (ICSE), 771--781 . Shahzad, M., Shafiq, M. Z. and Liu, A. X. 2012. A large scale exploratory analysis of software vulnerability life cycles. In Proceedings of the 34th International Conference on Software Engineering (ICSE), 771--781."},{"volume-title":"Proceedings of 2018 International Symposium on Computing and Networking (CANDAR), 1--10","author":"Feutrill A.","key":"e_1_3_2_1_78_1","unstructured":"Feutrill , A. , Ranathunga , D. , Yarom , Y. and Roughan , M . 2018. The effect of common vulnerability scoring system metrics on vulnerability exploit delay . In Proceedings of 2018 International Symposium on Computing and Networking (CANDAR), 1--10 . Feutrill, A., Ranathunga, D., Yarom, Y. and Roughan, M. 2018. The effect of common vulnerability scoring system metrics on vulnerability exploit delay. In Proceedings of 2018 International Symposium on Computing and Networking (CANDAR), 1--10."},{"key":"e_1_3_2_1_79_1","volume-title":"A look at the time delays in CVSS vulnerability scoring. Applied Computing and Informatics","author":"Ruohonen J.","year":"2017","unstructured":"Ruohonen , J. 2017. A look at the time delays in CVSS vulnerability scoring. Applied Computing and Informatics ( 2017 ). Ruohonen, J. 2017. A look at the time delays in CVSS vulnerability scoring. Applied Computing and Informatics (2017)."},{"volume-title":"Proceedings of 2019 International Conference on Cyberworlds (CW), 316--323","author":"Le B.","key":"e_1_3_2_1_80_1","unstructured":"Le , B. , Wang , G. , Nasim , M. and Babar , M. A . 2019. Gathering cyber threat intelligence from Twitter using novelty classification . In Proceedings of 2019 International Conference on Cyberworlds (CW), 316--323 . Le, B., Wang, G., Nasim, M. and Babar, M. A. 2019. Gathering cyber threat intelligence from Twitter using novelty classification. In Proceedings of 2019 International Conference on Cyberworlds (CW), 316--323."}],"event":{"name":"MSR '20: 17th International Conference on Mining Software Repositories","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Seoul Republic of Korea","acronym":"MSR '20"},"container-title":["Proceedings of the 17th International Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3379597.3387443","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3379597.3387443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:20Z","timestamp":1750200080000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3379597.3387443"}},"subtitle":["Mining Security Posts from Developer Question and Answer Websites with PU Learning"],"short-title":[],"issued":{"date-parts":[[2020,6,29]]},"references-count":80,"alternative-id":["10.1145\/3379597.3387443","10.1145\/3379597"],"URL":"https:\/\/doi.org\/10.1145\/3379597.3387443","relation":{},"subject":[],"published":{"date-parts":[[2020,6,29]]},"assertion":[{"value":"2020-09-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}