{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:56:59Z","timestamp":1785495419833,"version":"3.56.0"},"reference-count":51,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2016]]},"DOI":"10.1587\/transinf.2016edp7052","type":"journal-article","created":{"date-parts":[[2016,6,30]],"date-time":"2016-06-30T23:09:16Z","timestamp":1467328156000},"page":"1762-1775","source":"Crossref","is-referenced-by-count":21,"title":["Automated Duplicate Bug Report Detection Using Multi-Factor Analysis"],"prefix":"10.1587","volume":"E99.D","author":[{"given":"Jie","family":"ZOU","sequence":"first","affiliation":[{"name":"School of Software Engineering, Chongqing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"XU","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Chongqing University"},{"name":"Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengning","family":"YANG","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Chongqing University"},{"name":"Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"ZHANG","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Chongqing University"},{"name":"Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"ZENG","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Chongqing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sachio","family":"HIROKAWA","sequence":"additional","affiliation":[{"name":"Research Institute of Information Technology, Kyushu University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J. Anvik, L. Hiew, and G.C. Murphy, \u201cCoping with an open bug repository,\u201d Proceedings of the 2005 OOPSLA workshop on Eclipse technology eXchange-eclipse '05, New York, New York, USA, pp.35-39, ACM Press, 2005.","DOI":"10.1145\/1117696.1117704"},{"key":"2","unstructured":"[2] L. Hiew, Assisted detection of duplicate bug reports, Ph.D. thesis, The University Of British Columbia, 2006."},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] P. Runeson, M. Alexandersson, and O. Nyholm, \u201cDetection of duplicate defect reports using natural language processing,\u201d Software Engineering, 2007. ICSE 2007. 29th International Conference on, pp.499-510, IEEE, 2007.","DOI":"10.1109\/ICSE.2007.32"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] X. Wang, L. Zhang, T. Xie, J. Anvik, and J. Sun, \u201cAn approach to detecting duplicate bug reports using natural language and execution information,\u201d Proceedings of the 30th international conference on Software engineering, pp.461-470, ACM, 2008.","DOI":"10.1145\/1368088.1368151"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] N. Jalbert and W. Weimer, \u201cAutomated duplicate detection for bug tracking systems,\u201d Dependable Systems and Networks With FTCS and DCC, 2008. DSN 2008. IEEE International Conference on, pp.52-61, IEEE, 2008.","DOI":"10.1109\/DSN.2008.4630070"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] C. Sun, D. Lo, X. Wang, J. Jiang, and S.-C. Khoo, \u201cA discriminative model approach for accurate duplicate bug report retrieval,\u201d Proceedings of the 32nd ACM\/IEEE International Conference on Software Engineering-Volume 1, pp.45-54, ACM, 2010.","DOI":"10.1145\/1806799.1806811"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] A.T. Nguyen, T.T. Nguyen, T.N. Nguyen, D. Lo, and C. Sun, \u201cDuplicate bug report detection with a combination of information retrieval and topic modeling,\u201d Automated Software Engineering (ASE), 2012 Proceedings of the 27th IEEE\/ACM International Conference on, pp.70-79, IEEE, 2012.","DOI":"10.1145\/2351676.2351687"},{"key":"8","unstructured":"[8] G. Salton, The SMART retrieval system-experiments in automatic document processing, Prentice-Hall, 1971."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] A. Alipour, A. Hindle, and E. Stroulia, \u201cA Contextual Approach Towards More Accurate Duplicate Bug Report Detection,\u201d Proceedings of the 10th Working Conference on Mining Software Repositories, MSR '13, Piscataway, NJ, USA, pp.183-192, IEEE Press, 2013.","DOI":"10.1109\/MSR.2013.6624026"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] Y. Tian, C. Sun, and D. Lo, \u201cImproved Duplicate Bug Report Identification,\u201d 2012 16th European Conference on Software Maintenance and Reengineering, pp.385-390, IEEE, March 2012.","DOI":"10.1109\/CSMR.2012.48"},{"key":"11","unstructured":"[11] D.M. Blei, A.Y. Ng, and M.I. Jordan, \u201cLatent dirichlet allocation,\u201d Journal of Machine Learning Research, vol.3, pp.993-1022, 2003."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] G. Salton, A. Wong, and C.S. Yang, \u201cA vector space model for automatic indexing,\u201d Communications of the ACM, vol.18, no.11, pp.613-620, Nov. 1975.","DOI":"10.1145\/361219.361220"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] A. Sureka and P. Jalote, \u201cDetecting Duplicate Bug Report Using Character N-Gram-Based Features,\u201d 2010 Asia Pacific Software Engineering Conference, pp.366-374, IEEE, Nov. 2010.","DOI":"10.1109\/APSEC.2010.49"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] C. Sun, D. Lo, S.-C. Khoo, and J. Jiang, \u201cTowards more accurate retrieval of duplicate bug reports,\u201d 2011 26th IEEE\/ACM International Conference on Automated Software Engineering (ASE 2011), pp.253-262, IEEE, Nov. 2011.","DOI":"10.1109\/ASE.2011.6100061"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] C.-Z. Yang, H.-H. Du, S.-S. Wu, and X. Chen, \u201cDuplication Detection for Software Bug Reports Based on BM25 Term Weighting,\u201d Technologies and Applications of Artificial Intelligence (TAAI), 2012 Conference on, pp.33-38, IEEE, 2012.","DOI":"10.1109\/TAAI.2012.20"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] N. Kaushik and L. Tahvildari, \u201cA comparative study of the performance of ir models on duplicate bug detection,\u201d Software Maintenance and Reengineering (CSMR), 2012 16th European Conference on, pp.159-168, IEEE, 2012.","DOI":"10.1109\/CSMR.2012.78"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] J. Zhou and H. Zhang, \u201cLearning to rank duplicate bug reports,\u201d Proceedings of the 21st ACM international conference on Information and knowledge management, pp.852-861, ACM, 2012.","DOI":"10.1145\/2396761.2396869"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] J. Zhang, X. Wang, D. Hao, B. Xie, L. Zhang, and H. Mei, \u201cA survey on bug-report analysis,\u201d Science China Information Sciences, vol.58, no.2, pp.1-24, 2015.","DOI":"10.1007\/s11432-014-5241-2"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] K. Aggarwal, T. Rutgers, F. Timbers, A. Hindle, R. Greiner, and E. Stroulia, \u201cDetecting duplicate bug reports with software engineering domain knowledge,\u201d Software Analysis, Evolution and Reengineering (SANER), 2015 IEEE 22nd International Conference on, pp.211-220, IEEE, 2015.","DOI":"10.1109\/SANER.2015.7081831"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] F. Thung, P.S. Kochhar, and D. Lo, \u201cDupFinder: integrated tool support for duplicate bug report detection,\u201d Proceedings of the 29th ACM\/IEEE international conference on Automated software engineering, pp.871-874, ACM, 2014.","DOI":"10.1145\/2642937.2648627"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] A. Lazar, S. Ritchey, and B. Sharif, \u201cImproving the accuracy of duplicate bug report detection using textual similarity measures,\u201d Proceedings of the 11th Working Conference on Mining Software Repositories, pp.308-311, ACM, 2014.","DOI":"10.1145\/2597073.2597088"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] S. Rastkar, G. Murphy, and G. Murray, \u201cAutomatic Summarization of Bug Reports,\u201d IEEE Trans. Softw. Eng., vol.40, no.4, pp.366-380, 2014.","DOI":"10.1109\/TSE.2013.2297712"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] S. Banerjee, B. Cukic, and D. Adjeroh, \u201cAutomated Duplicate Bug Report Classification Using Subsequence Matching,\u201d 2012 IEEE 14th International Symposium on High-Assurance Systems Engineering, pp.74-81, IEEE, Oct. 2012.","DOI":"10.1109\/HASE.2012.38"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] M. Amoui, N. Kaushik, A. Al-Dabbagh, L. Tahvildari, S. Li, and W. Liu, \u201cSearch-based duplicate defect detection: an industrial experience,\u201d Mining Software Repositories (MSR), 2013 10th IEEE Working Conference on, pp.173-182, IEEE, 2013.","DOI":"10.1109\/MSR.2013.6624025"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] J. Lerch and M. Mezini, \u201cFinding Duplicates of Your Yet Unwritten Bug Report,\u201d 2013 17th European Conference on Software Maintenance and Reengineering, pp.69-78, IEEE, March 2013.","DOI":"10.1109\/CSMR.2013.17"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] R.P. Gopalan and A. Krishna, \u201cDuplicate Bug Report Detection Using Clustering,\u201d Software Engineering Conference (ASWEC), 2014 23rd Australian, pp.104-109, IEEE, 2014.","DOI":"10.1109\/ASWEC.2014.31"},{"key":"27","unstructured":"[27] T. Zhang and B. Lee, \u201cA Novel Technique for Duplicate Detection and Classification of Bug Reports,\u201d IEICE Transactions on Information and Systems, vol.E97.D, no.7, pp.1756-1768, 2014."},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] P. Hooimeijer and W. Weimer, \u201cModeling bug report quality,\u201d Proceedings of the twenty-second IEEE\/ACM international conference on Automated software engineering, pp.34-43, ACM, 2007.","DOI":"10.1145\/1321631.1321639"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] N. Bettenburg, S. Just, A. Schr\u00f6ter, C. Weiss, R. Premraj, and T. Zimmermann, \u201cWhat makes a good bug report?,\u201d Proceedings of the 16th ACM SIGSOFT International Symposium on Foundations of software engineering, pp.308-318, ACM, 2008.","DOI":"10.1145\/1453101.1453146"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] T. Menzies and A. Marcus, \u201cAutomated severity assessment of software defect reports,\u201d Software Maintenance, 2008. ICSM 2008. IEEE International Conference on, pp.346-355, IEEE, 2008.","DOI":"10.1109\/ICSM.2008.4658083"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] H. Cunningham, D. Maynard, K. Bontcheva, and V. Tablan, \u201cGATE: an architecture for development of robust HLT applications,\u201d Proceedings of the 40th annual meeting on association for computational linguistics, pp.168-175, Association for Computational Linguistics, 2002.","DOI":"10.3115\/1073083.1073112"},{"key":"32","unstructured":"[32] O. Gospodnetic and E. Hatcher, Lucene, Manning, 2005."},{"key":"33","unstructured":"[33] A.K. McCallum, \u201cMallet: A machine learning for language toolkit,\u201d University of Massachusetts, 2002."},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] D. Blei and J. Lafferty, \u201cText mining: Theory and applications, chapter topic models,\u201d 2009.","DOI":"10.1201\/9781420059458.ch4"},{"key":"35","unstructured":"[35] J.D. Mcauliffe and D.M. Blei, \u201cSupervised topic models,\u201d Advances in Neural Information Processing Systems, pp.121-128, 2008."},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] S. Grant, J.R. Cordy, and D.B. Skillicorn, \u201cUsing topic models to support software maintenance,\u201d Software Maintenance and Reengineering (CSMR), 2012 16th European Conference on, pp.403-408, IEEE, 2012.","DOI":"10.1109\/CSMR.2012.51"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] S.W. Thomas, B. Adams, A.E. Hassan, and D. Blostein, \u201cValidating the use of topic models for software evolution,\u201d Source Code Analysis and Manipulation (SCAM), 2010 10th IEEE Working Conference on, pp.55-64, IEEE, 2010.","DOI":"10.1109\/SCAM.2010.13"},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] T.T. Nguyen, T.N. Nguyen, and T.M. Phuong, \u201cTopic-based defect prediction (nier track),\u201d Proceedings of the 33rd international conference on software engineering, pp.932-935, ACM, 2011.","DOI":"10.1145\/1985793.1985950"},{"key":"39","doi-asserted-by":"crossref","unstructured":"[39] Y. Fu, M. Yan, X. Zhang, L. Xu, D. Yang, and J.D. Kymer, \u201cAutomated Classification of Software Change Messages by Semi-supervised Latent Dirichlet Allocation,\u201d Information and Software Technology, vol.57, pp.369-377, 2014.","DOI":"10.1016\/j.infsof.2014.05.017"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[40] T. Hofmann, \u201cProbabilistic latent semantic indexing,\u201d Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, pp.50-57, ACM, 1999.","DOI":"10.1145\/312624.312649"},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] T.K. Moon, \u201cThe expectation-maximization algorithm,\u201d Signal processing magazine, IEEE, vol.13, no.6, pp.47-60, 1996.","DOI":"10.1109\/79.543975"},{"key":"42","doi-asserted-by":"crossref","unstructured":"[42] G. Casella and E.I. George, \u201cExplaining the Gibbs sampler,\u201d The American Statistician, vol.46, no.3, pp.167-174, 1992.","DOI":"10.1080\/00031305.1992.10475878"},{"key":"43","unstructured":"[43] G. Heinrich, \u201cParameter estimation for text analysis,\u201d Technical report, Univ. Leipzig, 2008."},{"key":"44","unstructured":"[44] W.B. Cavnar, J.M. Trenkle, and Others, \u201cN-gram-based text categorization,\u201d Ann Arbor MI, vol.48113, no.2, pp.161-175, 1994."},{"key":"45","unstructured":"[45] V. Ke\u0161elj, F. Peng, N. Cercone, and C. Thomas, \u201cN-gram-based author profiles for authorship attribution,\u201d Proceedings of the Conference Pacific Association for Computational Linguistics (PACLING), pp.255-264, 2003."},{"key":"46","doi-asserted-by":"crossref","unstructured":"[46] G. Kondrak, \u201cN-gram similarity and distance,\u201d String processing and information retrieval, vol.3772, pp.115-126, Springer, 2005.","DOI":"10.1007\/11575832_13"},{"key":"47","doi-asserted-by":"crossref","unstructured":"[47] Y. Miao, V. Keselj, and E.E. Milios, Comparing document clustering using n-grams, terms and words, Master's thesis, Dalhousie University, 2004.","DOI":"10.1145\/1099554.1099665"},{"key":"48","doi-asserted-by":"crossref","unstructured":"[48] M. Shafiei, S. Wang, R. Zhang, E. Milios, B. Tang, J. Tougas, and R. Spiteri, \u201cDocument representation and dimension reduction for text clustering,\u201d Data Engineering Workshop, 2007 IEEE 23rd International Conference on, pp.770-779, IEEE, 2007.","DOI":"10.1109\/ICDEW.2007.4401066"},{"key":"49","doi-asserted-by":"crossref","unstructured":"[49] Y.F. Li, J.T. Kwok, and Z.H. Zhou, \u201cCost-Sensitive Semi-Supervised Support Vector Machine,\u201d AAAI, pp.500-505, 2010.","DOI":"10.1609\/aaai.v24i1.7661"},{"key":"50","doi-asserted-by":"crossref","unstructured":"[50] H.M. Wallach, I. Murray, R. Salakhutdinov, and D. Mimno, \u201cEvaluation methods for topic models,\u201d Proceedings of the 26th Annual International Conference on Machine Learning, pp.1105-1112, ACM, 2009.","DOI":"10.1145\/1553374.1553515"},{"key":"51","doi-asserted-by":"crossref","unstructured":"[51] S.W. Thomas, B. Adams, A.E. Hassan, and D. Blostein, \u201cStudying software evolution using topic models,\u201d Science of Computer Programming, vol.80, pp.457-479, 2014.","DOI":"10.1016\/j.scico.2012.08.003"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E99.D\/7\/E99.D_2016EDP7052\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T23:24:50Z","timestamp":1748993090000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E99.D\/7\/E99.D_2016EDP7052\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"references-count":51,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2016]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2016edp7052","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}