{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T18:23:48Z","timestamp":1781375028228,"version":"3.54.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:00:00Z","timestamp":1578009600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:00:00Z","timestamp":1578009600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["Grant No. 1633437"],"award-info":[{"award-number":["Grant No. 1633437"]}],"id":[{"id":"10.13039\/501100008982","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":[[2020,3]]},"DOI":"10.1007\/s10664-019-09786-7","type":"journal-article","created":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T15:02:36Z","timestamp":1578063756000},"page":"1136-1167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["ALFAA: Active Learning Fingerprint based Anti-Aliasing for correcting developer identity errors in version control systems"],"prefix":"10.1007","volume":"25","author":[{"given":"Sadika","family":"Amreen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Audris","family":"Mockus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Russell","family":"Zaretzki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Bogart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxia","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,1,3]]},"reference":[{"key":"9786_CR1","unstructured":"Badashian AS, Esteki A, Gholipour A, Hindle A, Stroulia E (2014) Involvement, contribution and influence in github and stack overflow. In: Proceedings of 24th annual international conference on computer science and software engineering, pp 19\u201333. IBM Corp"},{"key":"9786_CR2","first-page":"1","volume":"24","author":"S Baltes","year":"2018","unstructured":"Baltes S, Diehl S (2018) Usage and attribution of stack overflow code snippets in github projects. Empir Softw Eng 24:1\u201337","journal-title":"Empir Softw Eng"},{"key":"9786_CR3","doi-asserted-by":"publisher","unstructured":"Bird C, Gourley A, Devanbu P, Gertz M, Swaminathan A (2006) Mining email social networks. In: Proceedings of the 2006 international workshop on mining software repositories, MSR \u201906. https:\/\/doi.org\/10.1145\/1137983.1138016. ACM, New York, pp 137\u2013143","DOI":"10.1145\/1137983.1138016"},{"key":"9786_CR4","doi-asserted-by":"crossref","unstructured":"Bird C, Rigby PC, Barr ET, Hamilton DJ, German DM, Devanbu P (2009) The promises and perils of mining git","DOI":"10.1109\/MSR.2009.5069475"},{"issue":"5","key":"9786_CR5","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1086\/228631","volume":"92","author":"P Bonacich","year":"1987","unstructured":"Bonacich P (1987) Power and centrality: A family of measures. Am J Soc 92 (5):1170\u20131182. https:\/\/doi.org\/10.1086\/228631","journal-title":"Am J Soc"},{"key":"9786_CR6","doi-asserted-by":"crossref","DOI":"10.4159\/9780674029095","volume-title":"Structural holes","author":"RS Burt","year":"1992","unstructured":"Burt RS (1992) Structural holes. Harvard University Press, Harvard"},{"key":"9786_CR7","doi-asserted-by":"crossref","unstructured":"Cataldo M, Wagstrom PA, Herbsleb JD, Carley KM (2006) Identification of coordination requirements: implications for the design of collaboration and awareness tools. In: Proceedings of the 2006 20th anniversary conference on Computer supported cooperative work, pp 353\u2013362. ACM","DOI":"10.1145\/1180875.1180929"},{"key":"9786_CR8","doi-asserted-by":"crossref","unstructured":"Cataldo M, Herbsleb JD, Carley KM (2008) Socio-technical congruence: a framework for assessing the impact of technical and work dependencies on software development productivity. In: Proceedings of the Second ACM-IEEE international symposium on Empirical software engineering and measurement, pp 2\u201311. ACM","DOI":"10.1145\/1414004.1414008"},{"key":"9786_CR9","doi-asserted-by":"publisher","unstructured":"Christen P (2006) A comparison of personal name matching: Techniques and practical issues. In: 6th IEEE international conference on data mining - workshops (ICDMW\u201906), pp 290\u2013294. https:\/\/doi.org\/10.1109\/ICDMW.2006.2","DOI":"10.1109\/ICDMW.2006.2"},{"key":"9786_CR10","unstructured":"Cohen WW, Ravikumar P, Fienberg SE (2003) A comparison of string metrics for matching names and records. In: KDD Workshop on data cleaning and object consolidation"},{"issue":"4","key":"9786_CR11","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/MS.2013.68","volume":"30","author":"J Czerwonka","year":"2013","unstructured":"Czerwonka J, Nagappan N, Schulte W, Murphy B (2013) Codemine: Building a software development data analytics platform at microsoft. IEEE Softw 30 (4):64\u201371","journal-title":"IEEE Softw"},{"issue":"1","key":"9786_CR12","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1080\/07421222.1996.11518117","volume":"13","author":"DT Edberg","year":"1996","unstructured":"Edberg DT, Bowman BJ (1996) User-developed applications: An empirical study of application quality and developer productivity. J Manag Inf Syst 13(1):167\u2013185","journal-title":"J Manag Inf Syst"},{"issue":"328","key":"9786_CR13","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"IP Fellegi","year":"1969","unstructured":"Fellegi IP, Sunter AB (1969) A theory for record linkage. J Am Stat Assoc 64(328):1183\u20131210. https:\/\/doi.org\/10.1080\/01621459.1969.10501049. https:\/\/www.tandfonline.com\/doi\/abs\/10.1080\/01621459.1969.10501049","journal-title":"J Am Stat Assoc"},{"issue":"3","key":"9786_CR14","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/0378-8733(78)90021-7","volume":"1","author":"LC Freeman","year":"1978","unstructured":"Freeman LC (1978) Centrality in social networks conceptual clarification. Soc Netw 1(3):215\u2013239. https:\/\/doi.org\/10.1016\/0378-8733(78)90021-7. http:\/\/www.sciencedirect.com\/science\/article\/pii\/0378873378900217","journal-title":"Soc Netw"},{"key":"9786_CR15","doi-asserted-by":"crossref","unstructured":"German DM (2004) Mining cvs repositories, the softchange experience. In: 1st international workshop on mining software repositories, pp 17\u201321. Citeseer","DOI":"10.1049\/ic:20040469"},{"key":"9786_CR16","unstructured":"German D, Mockus A (2003) Automating the measurement of open source projects. In: Proceedings of the 3rd workshop on open source software engineering, pp 63\u201367. University College Cork Cork Ireland"},{"issue":"5","key":"9786_CR17","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1007\/s10664-014-9332-x","volume":"20","author":"M Gharehyazie","year":"2015","unstructured":"Gharehyazie M, Posnett D, Vasilescu B, Filkov V (2015) Developer initiation and social interactions in oss: A case study of the apache software foundation. Empirical Softw Eng 20(5):1318\u20131353. https:\/\/doi.org\/10.1007\/s10664-014-9332-x","journal-title":"Empirical Softw Eng"},{"issue":"8","key":"9786_CR18","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1016\/j.scico.2011.11.004","volume":"78","author":"M Goeminne","year":"2013","unstructured":"Goeminne M, Mens T (2013) A comparison of identity merge algorithms for software repositories. Sci Comput Progr 78(8):971\u2013986. https:\/\/doi.org\/10.1016\/j.scico.2011.11.004. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167642311002048","journal-title":"Sci Comput Progr"},{"issue":"1","key":"9786_CR19","doi-asserted-by":"publisher","first-page":"23","DOI":"10.20982\/tqmp.08.1.p023","volume":"8","author":"KA Hallgren","year":"2012","unstructured":"Hallgren KA (2012) Computing inter-rater reliability for observational data: an overview and tutorial. Tutorials in quantitative methods for psychology 8(1):23","journal-title":"Tutorials in quantitative methods for psychology"},{"key":"9786_CR20","doi-asserted-by":"crossref","unstructured":"Jergensen C, Sarma A, Wagstrom P (2011) The onion patch: migration in open source ecosystems. In: Proceedings of the 19th ACM SIGSOFT symposium and the 13th European conference on Foundations of software engineering, pp 70\u201380. ACM","DOI":"10.1145\/2025113.2025127"},{"key":"9786_CR21","doi-asserted-by":"crossref","unstructured":"Kouters E, Vasilescu B, Serebrenik A, van den Brand MGJ (2012) Who\u2019s who in gnome: using lsa to merge software repository identities. In: 28th IEEE international conference on software maintenance (ICSM). IEEE","DOI":"10.1109\/ICSM.2012.6405329"},{"issue":"6","key":"9786_CR22","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/2.769447","volume":"32","author":"S Lawrence","year":"1999","unstructured":"Lawrence S, Giles CL, Bollacker K (1999) Digital libraries and autonomous citation indexing. Computer 32(6):67\u201371. 10.1109\/2.769447","journal-title":"Computer"},{"key":"9786_CR23","unstructured":"Le Q, Mikolov T (2014) Distributed representation of sentences and documents. In: Proceedings of the 31 st international conference on machine learning. https:\/\/cs.stanford.edu\/quocle\/paragraph_vector.pdf, vol 32. JMLR, Beijing"},{"key":"9786_CR24","doi-asserted-by":"crossref","unstructured":"Ma Y, Bogart C, Amreen S, Zaretzki R, Mockus A (2019) World of code: An infrastructure for mining the universe of open source vcs data. In: Proceedings of the 2019 international conference on mining software repositories","DOI":"10.1109\/MSR.2019.00031"},{"key":"9786_CR25","first-page":"171","volume-title":"IFIP \u2013 The International Federation for Information Processing","author":"Juan Martinez-Romo","year":"2008","unstructured":"Martinez-Romo J, Robles G, Gonzalez-Barahona JM, Ortun\u0307o-Perez M (2008) Using social network analysis techniques to study collaboration between a floss community and a company. In: Russo B, Damiani E, Hissam S, Lundell B, Succi G (eds) Open source development, communities and quality. Springer, Boston, pp 171\u2013186"},{"key":"9786_CR26","doi-asserted-by":"crossref","unstructured":"Mockus A (2009a) Amassing and indexing a large sample of version control systems: towards the census of public source code history. In: 6th IEEE working conference on mining software repositories. IEEE. papers\/amassing.pdf","DOI":"10.1109\/MSR.2009.5069476"},{"key":"9786_CR27","doi-asserted-by":"crossref","unstructured":"Mockus A (2009b) Succession: Measuring transfer of code and developer productivity. In: Proceedings of the 31st international conference on software engineering, pp 67\u201377. IEEE Computer Society","DOI":"10.1109\/ICSE.2009.5070509"},{"key":"9786_CR28","doi-asserted-by":"crossref","unstructured":"Mockus A (2009c) Succession: Measuring transfer of code and developer productivity. In: 2009 international conference on software engineering. papers\/succession.pdf. ACM Press, Vancouver","DOI":"10.1109\/ICSE.2009.5070509"},{"key":"9786_CR29","doi-asserted-by":"crossref","unstructured":"Mockus A (2014) Engineering big data solutions. In: ICSE\u201914 FOSE, pp 85\u201399. http:\/\/dl.acm.org\/authorize?N14216","DOI":"10.1145\/2593882.2593889"},{"key":"9786_CR30","doi-asserted-by":"crossref","unstructured":"Mockus A, Herbsleb JD (2002) Expertise browser: a quantitative approach to identifying expertise. In: Proceedings of the 24th international conference on software engineering, pp 503\u2013512. ACM","DOI":"10.1145\/581339.581401"},{"key":"9786_CR31","unstructured":"Nagappan N, Murphy B, Basili V (2008) The influence of organizational structure on software quality. In: 2008 ACM\/IEEE 30th international conference on software engineering, pp 521\u2013530. IEEE"},{"key":"9786_CR32","doi-asserted-by":"publisher","unstructured":"Nesbitt A, Nickolls B (2017) Libraries.io open source repository and dependency metadata. https:\/\/doi.org\/10.5281\/zenodo.808273","DOI":"10.5281\/zenodo.808273"},{"key":"9786_CR33","unstructured":"Ostrouchov G, Chen WC, Schmidt D, Patel P (2012) Programming with big data in r. URL http:\/\/r-pbd.org"},{"issue":"9","key":"9786_CR34","first-page":"975","volume":"41","author":"K Petersen","year":"2011","unstructured":"Petersen K, Wohlin C (2011) Measuring the flow in lean software development. Software: Practice and experience 41(9):975\u2013996","journal-title":"Software: Practice and experience"},{"key":"9786_CR35","doi-asserted-by":"publisher","unstructured":"Pinzger M, Nagappan N, Murphy B (2008) Can developer-module networks predict failures?. In: Proceedings of the 16th ACM SIGSOFT international symposium on foundations of software engineering, SIGSOFT \u201908\/FSE-16. https:\/\/doi.org\/10.1145\/1453101.1453105. ACM, New York, pp 2\u201312","DOI":"10.1145\/1453101.1453105"},{"key":"9786_CR36","unstructured":"\u0158ehu\u0307\u0159ek R, Sojka P (2010) Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 workshop on new challenges for NLP frameworks. ELRA, Valletta, pp 45\u201350"},{"issue":"4","key":"9786_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1082983.1083162","volume":"30","author":"Gregorio Robles","year":"2005","unstructured":"Robles G, Gonzalez-Barahona JM (2005) Developer identification methods for integrated data from various sources. In: Proceedings of the 2005 international workshop on mining software repositories, MSR \u201905. https:\/\/doi.org\/10.1145\/1082983.1083162. ACM, New York, pp 1\u20135","journal-title":"ACM SIGSOFT Software Engineering Notes"},{"key":"9786_CR38","doi-asserted-by":"publisher","unstructured":"Sarawagi S, Bhamidipaty A (2002) Interactive deduplication using active learning. In: Proceedings of the 8th ACM SIGKDD international conference on knowledge discovery and data mining, KDD \u201902. https:\/\/doi.org\/10.1145\/775047.775087. ACM, New York, pp 269\u2013278","DOI":"10.1145\/775047.775087"},{"issue":"1","key":"9786_CR39","doi-asserted-by":"publisher","first-page":"61","DOI":"10.32614\/RJ-2010-017","volume":"2","author":"M Sariyar","year":"2010","unstructured":"Sariyar M, Borg A (2010) The recordlinkage package: Detecting errors in data. The R J 2(1):61\u201367 . https:\/\/journal.r-project.org\/archive\/2010-2\/RJournal_2010-_Sariyar+Borg.pdf","journal-title":"The R J"},{"issue":"1","key":"9786_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/aris.2009.1440430113","volume":"43","author":"NR Smalheiser","year":"2011","unstructured":"Smalheiser NR, Torvik VI (2011) Author name disambiguation. Annual Review of Information Science and Technology 43(1):1\u201343. https:\/\/doi.org\/10.1002\/aris.2009.1440430113. https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1002\/aris.2009.1440430113","journal-title":"Annual Review of Information Science and Technology"},{"key":"9786_CR41","unstructured":"Spencer D, Warfel T (2004) Card sorting: A definitive guide. Boxes and Arrows, pp 2"},{"key":"9786_CR42","doi-asserted-by":"crossref","unstructured":"Thung F, Bissyande TF, Lo D, Jiang L (2013) Network structure of social coding in github. In: 2013 17th European conference on software maintenance and reengineering, pp 323\u2013326. IEEE","DOI":"10.1109\/CSMR.2013.41"},{"key":"9786_CR43","doi-asserted-by":"crossref","unstructured":"Vasilescu B, Serebrenik A, Filkov V (2015) A data set for social diversity studies of github teams. In: Proceedings of the 12th working conference on mining software repositories, pp 514\u2013517. ACM. https:\/\/dl.acm.org\/citation.cfm?id=2820601","DOI":"10.1109\/MSR.2015.77"},{"key":"9786_CR44","doi-asserted-by":"crossref","unstructured":"Ventura SL, Nugent R, Fuchs ER (2015) Seeing the non-starts: (some) sources of bias in past disambiguation approaches and a new public tool leveraging labeled records. Elsevier","DOI":"10.1016\/j.respol.2014.12.010"},{"issue":"4","key":"9786_CR45","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1016\/j.socnet.2012.01.003","volume":"34","author":"DJ Wang","year":"2012","unstructured":"Wang DJ, Shi X, McFarland DA, Leskovec J (2012) Measurement error in network data: A re-classification. Soc Netw 34(4):396\u2013409","journal-title":"Soc Netw"},{"key":"9786_CR46","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1038\/30918","volume":"393","author":"DJ Watts","year":"1998","unstructured":"Watts DJ, Strogatz SH (1998) Collective dynamics of \u2018small-world\u2019 networks. Nature 393:440\u2013442. https:\/\/doi.org\/10.1038\/30918","journal-title":"Nature"},{"key":"9786_CR47","doi-asserted-by":"crossref","unstructured":"Wiese IS, da Silva JT, Steinmacher I, Treude C, Gerosa MA (2016) Who is who in the mailing list? comparing six disambiguation heuristics to identify multiple addresses of a participant. In: 2016 IEEE international conference on software maintenance and evolution (ICSME), pp 345\u2013355, DOI 10.1109\/ICSME.2016.13, (to appear in print)","DOI":"10.1109\/ICSME.2016.13"},{"key":"9786_CR48","volume-title":"Overview of record linkage and current research directions","author":"WE Winkler","year":"2006","unstructured":"Winkler WE (2006) Overview of record linkage and current research directions. Tech. rep., Bureau of the Census"},{"issue":"1","key":"9786_CR49","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/MS.2009.16","volume":"26","author":"T Wolf","year":"2009","unstructured":"Wolf T, Schr\u00f6ter A, Damian D, Panjer LD, Nguyen THD (2009) Mining task-based social networks to explore collaboration in software teams. IEEE Softw 26 (1):58\u201366. 10.1109\/MS.2009.16","journal-title":"IEEE Softw"},{"key":"9786_CR50","doi-asserted-by":"publisher","unstructured":"Xiong Y, Meng Z, Shen B, Yin W (2017) Mining developer behavior across github and stackoverflow. In: The 29th international conference on software engineering and knowledge engineering, pp 578\u2013583. https:\/\/doi.org\/10.18293\/SEKE2017-062","DOI":"10.18293\/SEKE2017-062"},{"issue":"2","key":"9786_CR51","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/2876443","volume":"25","author":"M Zhou","year":"2016","unstructured":"Zhou M, Mockus A, Ma X, Zhang L, Mei H (2016) Inflow and retention in oss communities with commercial involvement: A case study of three hybrid projects. ACM Transactions on Software Engineering and Methodology (TOSEM) 25(2):13","journal-title":"ACM Transactions on Software Engineering and Methodology (TOSEM)"},{"key":"9786_CR52","doi-asserted-by":"crossref","unstructured":"Zhu J, Wei J (2019) An empirical study of multiple names and email addresses in oss version control repositories. In: Proceedings of 16th international conference on mining software repositories (MSR). IEEE\/ACM","DOI":"10.1109\/MSR.2019.00068"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-019-09786-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10664-019-09786-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-019-09786-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T21:41:00Z","timestamp":1665351660000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10664-019-09786-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,3]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["9786"],"URL":"https:\/\/doi.org\/10.1007\/s10664-019-09786-7","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,3]]},"assertion":[{"value":"3 January 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}