{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T07:40:48Z","timestamp":1770536448845,"version":"3.49.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T00:00:00Z","timestamp":1643328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T00:00:00Z","timestamp":1643328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872272"],"award-info":[{"award-number":["61872272"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61640221"],"award-info":[{"award-number":["61640221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10664-021-10082-6","type":"journal-article","created":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T07:02:46Z","timestamp":1643353366000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["An empirical study of the effectiveness of IR-based bug localization for large-scale industrial projects"],"prefix":"10.1007","volume":"27","author":[{"given":"Wei","family":"Li","sequence":"first","affiliation":[]},{"given":"Qingan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yunlong","family":"Ming","sequence":"additional","affiliation":[]},{"given":"Weijiao","family":"Dai","sequence":"additional","affiliation":[]},{"given":"Shi","family":"Ying","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8758-8668","authenticated-orcid":false,"given":"Mengting","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,28]]},"reference":[{"key":"10082_CR1","doi-asserted-by":"crossref","unstructured":"Akbar S A, Kak A C (2020) A large-scale comparative evaluation of IR-based tools for bug localization. In: Proceedings of the 17th international conference on mining software repositories, pp 21\u201331","DOI":"10.1145\/3379597.3387474"},{"key":"10082_CR2","doi-asserted-by":"crossref","unstructured":"Antoniol G, Ayari K, Di Penta M, Khomh F, Gu\u00e9h\u00e9neuc Y -G (2008) Is it a bug or an enhancement?: a text-based approach to classify change requests. In: CASCON 8, pp 304\u2013318","DOI":"10.1145\/1463788.1463819"},{"key":"10082_CR3","doi-asserted-by":"publisher","unstructured":"Bettenburg N, Just S, Schr\u00f6ter A, Weiss C, Premraj R, Zimmermann T (2007) Quality of bug reports in Eclipse. In: Proceedings of the 2007 OOPSLA workshop on eclipse technology eXchange. https:\/\/doi.org\/10.1145\/1328279.1328284, pp 21\u201325","DOI":"10.1145\/1328279.1328284"},{"key":"10082_CR4","doi-asserted-by":"crossref","unstructured":"Bird C, Bachmann A, Aune E, Duffy J, Bernstein A, Filkov V, Devanbu P (2009) Fair and balanced?: bias in bug-fix datasets. In: Proceedings of the the 7th joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on the foundations of software engineering, pp 121\u2013130","DOI":"10.1145\/1595696.1595716"},{"key":"10082_CR5","doi-asserted-by":"crossref","unstructured":"Chang P C, Galley M, Manning C D (2008) Optimizing Chinese word segmentation for machine translation performance. In: Proceedings of the third workshop on statistical machine translation, pp 224\u2013232","DOI":"10.3115\/1626394.1626430"},{"issue":"5","key":"10082_CR6","doi-asserted-by":"publisher","first-page":"2947","DOI":"10.1007\/s10664-018-9672-z","volume":"24","author":"O Chaparro","year":"2019","unstructured":"Chaparro O, Florez J M, Marcus A (2019) Using bug descriptions to reformulate queries during text-retrieval-based bug localization. Empir Softw Eng 24 (5):2947\u20133007","journal-title":"Empir Softw Eng"},{"key":"10082_CR7","unstructured":"Devlin J, Chang M -W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"issue":"2","key":"10082_CR8","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1561\/1100000009","volume":"4","author":"MD Ekstrand","year":"2011","unstructured":"Ekstrand M D, Riedl J T, Konstan J A (2011) Collaborative filtering recommender systems. Foundations and Trends\u00ae;, in Human\u2013Computer Interaction 4(2):81\u2013173","journal-title":"Foundations and Trends\u00ae;, in Human\u2013Computer Interaction"},{"issue":"11","key":"10082_CR9","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1145\/32206.32212","volume":"30","author":"GW Furnas","year":"1987","unstructured":"Furnas G W, Landauer T K, Gomez L M, Dumais S T (1987) The vocabulary problem in human-system communication. Commun ACM 30 (11):964\u2013971. https:\/\/doi.org\/10.1145\/32206.32212","journal-title":"Commun ACM"},{"key":"10082_CR10","doi-asserted-by":"crossref","unstructured":"Gay G, Haiduc S, Marcus A, Menzies T (2009) On the use of relevance feedback in IR-based concept location. In: 2009 IEEE international conference on software maintenance, pp 351\u2013360","DOI":"10.1109\/ICSM.2009.5306315"},{"key":"10082_CR11","doi-asserted-by":"crossref","unstructured":"Gu X, Zhang H, Kim S (2018) Deep code search. In: 2018 IEEE\/ACM 40th international conference on software engineering (ICSE), pp 933\u2013944","DOI":"10.1145\/3180155.3180167"},{"key":"10082_CR12","doi-asserted-by":"crossref","unstructured":"Herzig K, Just S, Zeller A (2013) It\u2019s not a bug, it\u2019s a feature: how misclassification impacts bug prediction. In: Proceedings of the 2013 international conference on software engineering, pp 392\u2013401","DOI":"10.1109\/ICSE.2013.6606585"},{"key":"10082_CR13","doi-asserted-by":"crossref","unstructured":"Joachims T, Swaminathan A, Schnabel T (2017) Unbiased learning-to-rank with biased feedback. In: Proceedings of the tenth ACM international conference on web search and data mining, pp 781\u2013789","DOI":"10.1145\/3018661.3018699"},{"key":"10082_CR14","doi-asserted-by":"crossref","unstructured":"Kim S, Zimmermann T, Whitehead E J Jr, Zeller A (2007) Predicting faults from cached history. In: Proceedings of the 29th international conference on Software Engineering, pp 489\u2013498","DOI":"10.1109\/ICSE.2007.66"},{"key":"10082_CR15","doi-asserted-by":"crossref","unstructured":"Kim S, Zhang H, Wu R, Gong L (2011a) Dealing with noise in defect prediction. In: 2011 33rd international conference on software engineering (ICSE), pp 481\u2013490","DOI":"10.1145\/1985793.1985859"},{"issue":"11","key":"10082_CR16","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1109\/TSE.2013.24","volume":"39","author":"D Kim","year":"2011","unstructured":"Kim D, Tao Y, Kim S, Zeller A (2011b) Where should we fix this bug? A two-phase recommendation model. IEEE Trans Softw Eng 39 (11):1597\u20131610. https:\/\/doi.org\/10.1109\/TSE.2013.24","journal-title":"IEEE Trans Softw Eng"},{"key":"10082_CR17","doi-asserted-by":"crossref","unstructured":"Kochhar P S, Xia X, Lo D, Li S (2016) Practitioners\u2019 expectations on automated fault localization. In: International symposium on software testing & analysis, pp 165\u2013176","DOI":"10.1145\/2931037.2931051"},{"key":"10082_CR18","doi-asserted-by":"crossref","unstructured":"Lam A N, Nguyen A T, Nguyen H A, Nguyen T N (2015) Combining deep learning with information retrieval to localize buggy files for bug reports (n). In: 2015 30th IEEE\/ACM international conference on automated software engineering (ASE), pp 476\u2013481","DOI":"10.1109\/ASE.2015.73"},{"key":"10082_CR19","doi-asserted-by":"crossref","unstructured":"Lam A N, Nguyen A T, Nguyen H A, Nguyen T N (2017) Bug localization with combination of deep learning and information retrieval. In: 2017 IEEE\/ACM 25th international conference on program comprehension (ICPC), pp 218\u2013229","DOI":"10.1109\/ICPC.2017.24"},{"key":"10082_CR20","doi-asserted-by":"crossref","unstructured":"Le T -D B, Thung F, Lo D (2014) Predicting effectiveness of IR-based bug localization techniques. In: 2014 IEEE 25th international symposium on software reliability engineering, pp 335\u2013345","DOI":"10.1109\/ISSRE.2014.39"},{"key":"10082_CR21","doi-asserted-by":"crossref","unstructured":"Le T -D B, Thung F, Lo D (2017) Will this localization tool be effective for this bug? Mitigating the impact of unreliability of information retrieval based bug localization tools. Empir Softw Eng 22(4):1\u201343","DOI":"10.1007\/s10664-016-9484-y"},{"key":"10082_CR22","doi-asserted-by":"crossref","unstructured":"Lee J, Kim D, Bissyand\u00e9 T F, Jung W, Le Traon Y (2018) Bench4BL: reproducibility study on the performance of IR-based bug localization. In: Proceedings of the 27th ACM SIGSOFT international symposium on software testing and analysis, pp 61\u201372","DOI":"10.1145\/3213846.3213856"},{"issue":"9","key":"10082_CR23","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1016\/j.infsof.2010.04.002","volume":"52","author":"SK Lukins","year":"2010","unstructured":"Lukins S K, Kraft N A, Etzkorn L H (2010) Bug localization using latent dirichlet allocation. Inf Softw Technol 52(9):972\u2013990","journal-title":"Inf Softw Technol"},{"key":"10082_CR24","doi-asserted-by":"crossref","unstructured":"Mann H B, Whitney D R (1947) On a test of whether one of two random variables is stochastically larger than the other. Ann Math Stat 50\u201360","DOI":"10.1214\/aoms\/1177730491"},{"issue":"1","key":"10082_CR25","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1017\/S1351324909005129","volume":"16","author":"C Manning","year":"2010","unstructured":"Manning C, Raghavan P, Sch\u00fctze H (2010) Introduction to information retrieval. Nat Lang Eng 16(1):100\u2013103","journal-title":"Nat Lang Eng"},{"key":"10082_CR26","doi-asserted-by":"crossref","unstructured":"Mills C, Haiduc S (2017) The impact of retrieval direction on ir-based traceability link recovery. In: 2017 IEEE\/ACM 39th international conference on software engineering: new ideas and emerging technologies results track (ICSE-NIER), pp 51\u201354","DOI":"10.1109\/ICSE-NIER.2017.14"},{"key":"10082_CR27","doi-asserted-by":"crossref","unstructured":"Mills C, Bavota G, Haiduc S, Oliveto R, Marcus A, De Lucia A (2017) Predicting query quality for applications of text retrieval to software engineering tasks. In: ACM Trans Softw Eng Methodol (TOSEM), vol 26, pp 1\u201345","DOI":"10.1145\/3078841"},{"issue":"5","key":"10082_CR28","doi-asserted-by":"publisher","first-page":"3086","DOI":"10.1007\/s10664-020-09823-w","volume":"25","author":"C Mills","year":"2020","unstructured":"Mills C, Parra E, Pantiuchina J, Bavota G, Haiduc S (2020) On the relationship between bug reports and queries for text retrieval-based bug localization. Empir Softw Eng 25(5):3086\u20133127","journal-title":"Empir Softw Eng"},{"key":"10082_CR29","doi-asserted-by":"crossref","unstructured":"Murali V, Gross L, Qian R, Chandra S (2020) Industry-scale IR-based bug localization: a perspective from Facebook. arXiv:2010.09977","DOI":"10.1109\/ICSE-SEIP52600.2021.00028"},{"key":"10082_CR30","doi-asserted-by":"crossref","unstructured":"Nguyen A T, Nguyen T T, Al-Kofahi J, Nguyen H V, Nguyen T N (2011) A topic-based approach for narrowing the search space of buggy files from a bug report. In: Proceedings of the 2011 26th IEEE\/ACM international conference on automated software engineering, pp 263\u2013272","DOI":"10.1109\/ASE.2011.6100062"},{"key":"10082_CR31","first-page":"223","volume":"33","author":"DW Oard","year":"1998","unstructured":"Oard D W, Diekema A R (1998) Cross-language information retrieval. Annu Rev Inf Sci Technol (ARIST) 33:223\u201356","journal-title":"Annu Rev Inf Sci Technol (ARIST)"},{"key":"10082_CR32","volume-title":"Software product lines: patterns and practice","author":"C Paul","year":"2002","unstructured":"Paul C, Linda N (2002) Software product lines: patterns and practice. Addison-Wesley, Boston"},{"issue":"6","key":"10082_CR33","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1109\/TSE.2007.1016","volume":"33","author":"D Poshyvanyk","year":"2007","unstructured":"Poshyvanyk D, Gueheneuc Y -G, Marcus A, Antoniol G, Rajlich V (2007) Feature location using probabilistic ranking of methods based on execution scenarios and information retrieval. IEEE Trans Softw Eng 33(6):420\u2013432","journal-title":"IEEE Trans Softw Eng"},{"key":"10082_CR34","doi-asserted-by":"crossref","unstructured":"Pingclasai N, Hata H, Matsumoto K -I (2013) Classifying bug reports to bugs and other requests using topic modeling. In: 2013 20th Asia-Pacific software engineering conference (APSEC) 2, pp 13\u201318","DOI":"10.1109\/APSEC.2013.105"},{"key":"10082_CR35","doi-asserted-by":"crossref","unstructured":"Qin H, Sun X (2018) Classifying bug reports into bugs and non-bugs using LSTM. In: Proceedings of the tenth asia-pacific symposium on Internetware, p 20","DOI":"10.1145\/3275219.3275239"},{"key":"10082_CR36","doi-asserted-by":"crossref","unstructured":"Rahman M M, Roy C (2018a) Poster: improving bug localization with report quality dynamics and query reformulation. In: 2018 IEEE\/ACM 40th international conference on software engineering: companion (ICSE-companion), pp 348\u2013349","DOI":"10.1145\/3183440.3195003"},{"key":"10082_CR37","doi-asserted-by":"crossref","unstructured":"Rahman M M, Roy C K (2018b) Improving ir-based bug localization with context-aware query reformulation. In: Proceedings of the 2018 26th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering, pp 621\u2013632","DOI":"10.1145\/3236024.3236065"},{"key":"10082_CR38","doi-asserted-by":"crossref","unstructured":"Rao S, Kak A (2011) Retrieval from software libraries for bug localization: a comparative study of generic and composite text model. In: Proceedings of the 8th working conference on mining software repositories, pp 43\u201352","DOI":"10.1145\/1985441.1985451"},{"key":"10082_CR39","doi-asserted-by":"crossref","unstructured":"Saha R K, Lease M, Khurshid S, Perry D E (2013) Improving bug localization using structured information retrieval. In: 2013 28th IEEE\/ACM international conference on automated software engineering (ASE), pp 345\u2013355","DOI":"10.1109\/ASE.2013.6693093"},{"key":"10082_CR40","doi-asserted-by":"crossref","unstructured":"Saha R K, Lawall J, Khurshid S, Perry D E (2014) On the effectiveness of information retrieval based bug localization for c programs. In: 2014 IEEE international conference on software maintenance and evolution, pp 161\u2013170","DOI":"10.1109\/ICSME.2014.38"},{"key":"10082_CR41","doi-asserted-by":"crossref","unstructured":"Schroter A, Schr\u00f6ter A, Bettenburg N, Premraj R (2010) Do stack traces help developers fix bugs?. In: 2010 7th IEEE working conference on mining software repositories (MSR 2010), pp 118\u2013121","DOI":"10.1109\/MSR.2010.5463280"},{"key":"10082_CR42","doi-asserted-by":"crossref","unstructured":"Sisman B, Kak A C (2012) Incorporating version histories in information retrieval based bug localization. In: 2012 9th IEEE working conference on mining software repositories (MSR), pp 50\u201359","DOI":"10.1109\/MSR.2012.6224299"},{"key":"10082_CR43","doi-asserted-by":"crossref","unstructured":"Wan Y, Zhao Z, Yang M, Xu G, Ying H, Wu J, Yu P S (2018) Improving automatic source code summarization via deep reinforcement learning. In: Proceedings of the 33rd ACM\/IEEE international conference on automated software engineering, pp 397\u2013407","DOI":"10.1145\/3238147.3238206"},{"key":"10082_CR44","doi-asserted-by":"crossref","unstructured":"Wang S, Lo D (2014) Version history, similar report, and structure: putting them together for improved bug localization. In: Proceedings of the 22nd international conference on program comprehension, pp 53\u201363","DOI":"10.1145\/2597008.2597148"},{"key":"10082_CR45","doi-asserted-by":"crossref","unstructured":"Wang Q, Parnin C, Orso A (2015) Evaluating the usefulness of IR-based fault localization techniques. In: Proceedings of the 2015 international symposium on software testing and analysis, pp 1\u201311","DOI":"10.1145\/2771783.2771797"},{"key":"10082_CR46","doi-asserted-by":"crossref","unstructured":"Wen M, Wu R, Cheung S -C (2016) Locus: locating bugs from software changes. In: 2016 31St IEEE\/ACM international conference on automated software engineering (ASE), pp 262\u2013273","DOI":"10.1145\/2970276.2970359"},{"key":"10082_CR47","doi-asserted-by":"crossref","unstructured":"Wong C -P, Xiong Y, Zhang H, Hao D, Zhang L, Mei H (2014) Boosting bug-report-oriented fault localization with segmentation and stack-trace analysis. In: 2014 IEEE international conference on software maintenance and evolution, pp 181\u2013190","DOI":"10.1109\/ICSME.2014.40"},{"issue":"8","key":"10082_CR48","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1109\/TSE.2016.2521368","volume":"42","author":"WE Wong","year":"2016","unstructured":"Wong W E, Gao R, Li Y, Abreu R, Wotawa F (2016) A survey on software fault localization. IEEE Trans Softw Eng 42(8):707\u2013740","journal-title":"IEEE Trans Softw Eng"},{"key":"10082_CR49","doi-asserted-by":"crossref","unstructured":"Xia X, Lo D, Wang X, Zhang C, Wang X (2014) Cross-language bug localization. In: Proceedings of the 22nd international conference on program comprehension, pp 275\u2013278","DOI":"10.1145\/2597008.2597788"},{"key":"10082_CR50","unstructured":"Xuan H, Li M (2017) Enhancing the unified features to locate buggy files by exploiting the sequential nature of source code. In: IJCAI, pp 1909\u20131915"},{"key":"10082_CR51","unstructured":"Xuan H, Li M, Zhou Z -H (2016) Learning unified features from natural and programming languages for locating buggy source code. In: IJCAI, pp 1606\u20131612"},{"key":"10082_CR52","doi-asserted-by":"crossref","unstructured":"Ye X, Bunescu R, Liu C (2014) Learning to rank relevant files for bug reports using domain knowledge. In: Proceedings of the 22nd ACM SIGSOFT international symposium on foundations of software engineering, pp 689\u2013699","DOI":"10.1145\/2635868.2635874"},{"key":"10082_CR53","doi-asserted-by":"crossref","unstructured":"Ye X, Shen H, Ma X, Bunescu R, 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, pp 404\u2013415","DOI":"10.1145\/2884781.2884862"},{"key":"10082_CR54","doi-asserted-by":"crossref","unstructured":"Youm K C, Ahn J, Kim J, Lee E (2015) Bug localization based on code change histories and bug reports. In: 2015 Asia-pacific software engineering conference (APSEC), pp 190\u2013197","DOI":"10.1109\/APSEC.2015.23"},{"key":"10082_CR55","doi-asserted-by":"crossref","unstructured":"Zhang H (2009) An investigation of the relationships between lines of code and defects. In: 2009 IEEE international conference on software maintenance, pp 274\u2013283","DOI":"10.1109\/ICSM.2009.5306304"},{"key":"10082_CR56","doi-asserted-by":"crossref","unstructured":"Zhao L, Callan J (2012) Automatic term mismatch diagnosis for selective query expansion. In: Proceedings of the 35th international ACM SIGIR conference on research and development in information retrieva, pp 515\u2013524","DOI":"10.1145\/2348283.2348354"},{"issue":"5","key":"10082_CR57","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/TSE.2010.63","volume":"36","author":"T Zimmermann","year":"2010","unstructured":"Zimmermann T, Premraj R, Bettenburg N, Just S, Schroter A, Weiss C (2010) What makes a good bug report? IEEE Trans Softw Eng 36 (5):618\u2013643. https:\/\/doi.org\/10.1109\/TSE.2010.63","journal-title":"IEEE Trans Softw Eng"},{"key":"10082_CR58","doi-asserted-by":"crossref","unstructured":"Zhou J, Zhang H, Lo D (2012) Where should the bugs be fixed? more accurate information retrieval-based bug localization based on bug reports. In: 2012 34th international conference on software engineering (ICSE), pp 14\u201324","DOI":"10.1109\/ICSE.2012.6227210"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-021-10082-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-021-10082-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-021-10082-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,12]],"date-time":"2022-04-12T13:30:48Z","timestamp":1649770248000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-021-10082-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,28]]},"references-count":58,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["10082"],"URL":"https:\/\/doi.org\/10.1007\/s10664-021-10082-6","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,28]]},"assertion":[{"value":"10 November 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"47"}}