{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T03:27:29Z","timestamp":1782876449079,"version":"3.54.5"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2008,10,15]],"date-time":"2008-10-15T00:00:00Z","timestamp":1224028800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2009,4]]},"DOI":"10.1007\/s10618-008-0118-x","type":"journal-article","created":{"date-parts":[[2008,10,14]],"date-time":"2008-10-14T19:26:54Z","timestamp":1224012414000},"page":"300-336","source":"Crossref","is-referenced-by-count":192,"title":["Sourcerer: mining and searching internet-scale software repositories"],"prefix":"10.1007","volume":"18","author":[{"given":"Erik","family":"Linstead","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sushil","family":"Bajracharya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trung","family":"Ngo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Rigor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristina","family":"Lopes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre","family":"Baldi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2008,10,15]]},"reference":[{"key":"118_CR1","unstructured":"Sun Java Coding Standards. http:\/\/java.sun.com\/docs\/codeconv\/"},{"key":"118_CR2","unstructured":"Koders web site. http:\/\/www.koders.com"},{"key":"118_CR3","unstructured":"Krugle web site. http:\/\/www.krugle.com"},{"key":"118_CR4","unstructured":"Codase web site. http:\/\/www.Codase.com"},{"key":"118_CR5","unstructured":"Csourcesearch web site. http:\/\/csourcesearch.net\/"},{"key":"118_CR6","unstructured":"Google CodeSearch web site. http:\/\/www.google.com\/codesearch"},{"key":"118_CR7","unstructured":"SparsJ Search System. http:\/\/demo.spars.info\/"},{"key":"118_CR8","unstructured":"Andrzejewski D, Mulhern A, Liblit B, Zhu X (2007) Statistical debugging using latent topic models. In: Matwin S, Mladenic D (eds) 18th European conference on machine learning. Warsaw, Poland (to appear)"},{"key":"118_CR9","doi-asserted-by":"crossref","unstructured":"Anvik J, Hiew L, Murphy GC (2006) Who should fix this bug? In: ICSE \u201906: proceeding of the 28th international conference on Software engineering. ACM, New York, pp 361\u2013370","DOI":"10.1145\/1134285.1134336"},{"key":"118_CR10","unstructured":"Baeza-Yates RA, Ribeiro-Neto BA (1999) Modern information retrieval. ACM Press\/Addison-Wesley"},{"key":"118_CR11","doi-asserted-by":"crossref","unstructured":"Baldi P, Frasconi P, Smyth P (2003) Modeling the internet and the web: probabilistic methods and algorithms. Wiley","DOI":"10.1002\/047086799X"},{"key":"118_CR12","doi-asserted-by":"crossref","unstructured":"Baldi P, Lopes C, Linstead E, Bajracharya S (2008) A theory of aspects as latent topics. In: OOPSLA \u201908: proceedings of the 23rd annual ACM SIGPLAN conference on object-oriented programming systems, languages, and applications, Nashville, TN. ACM, New York, NY (to appear)","DOI":"10.1145\/1449764.1449807"},{"key":"118_CR13","first-page":"147","volume-title":"Advances in neural information processing systems, vol 18","author":"D Blei","year":"2006","unstructured":"Blei D, Lafferty J (2006) Correlated topic models. In: Weiss Y, Sch\u00f6lkopf B, Platt J (eds) Advances in neural information processing systems, vol 18. MIT Press, Cambridge, MA, pp 147\u2013154"},{"key":"118_CR14","first-page":"993","volume":"3","author":"D Blei","year":"2003","unstructured":"Blei D, Ng A, Jordan M (2003) Latent dirichlet allocation. J Mach Learn Res 3: 993\u20131022","journal-title":"J Mach Learn Res"},{"key":"118_CR15","unstructured":"Brill E (1994) Some advances in transformation-based part of speech tagging. In: National conference on artificial intelligence. pp 722\u2013727"},{"issue":"1","key":"118_CR16","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1145\/1067268.1067270","volume":"39","author":"W Buntine","year":"2005","unstructured":"Buntine W (2005) Open source search: a data mining platform. SIGIR Forum 39(1): 4\u201310","journal-title":"SIGIR Forum"},{"key":"118_CR17","doi-asserted-by":"crossref","first-page":"4133","DOI":"10.1093\/bioinformatics\/bti683","volume":"21","author":"J Chen","year":"2005","unstructured":"Chen J, Swamidass SJ, Dou Y, Bruand J, Baldi P (2005) ChemDB: a public database of small molecules and related chemoinformatics resources. Bioinformatics 21: 4133\u20134139","journal-title":"Bioinformatics"},{"issue":"10","key":"118_CR18","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1109\/TSE.2007.1019","volume":"33","author":"G Concas","year":"2007","unstructured":"Concas G, Marchesi M, Pinna S, Serra N (2007) Power-laws in a large object-oriented software system. IEEE Trans Softw Eng 33(10): 687\u2013708","journal-title":"IEEE Trans Softw Eng"},{"key":"118_CR19","unstructured":"Cox A, Clarke C, Sim S (1999) A model independent source code repository. In: CASCON \u201999: proceedings of the 1999 conference of the centre for advanced studies on collaborative research. IBM Press, p 1"},{"issue":"6","key":"118_CR20","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"S Deerwester","year":"1990","unstructured":"Deerwester S, Dumais S, Landauer T, Furnas G, Harshman R (1990) Indexing by latent semantic analysis. J Am Soc Inf Sci 41(6): 391\u2013407","journal-title":"J Am Soc Inf Sci"},{"issue":"4","key":"118_CR21","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1147\/sj.364.0564","volume":"36","author":"P Finnigan","year":"1997","unstructured":"Finnigan P, Holt R, Kalas I, Kerr S, Kontogiannis K, Mueller H, Mylopoulos J, Perelgut S, Stanley M, Wong K (1997) The software bookshelf. IBM Sys J 36(4): 564\u2013593","journal-title":"IBM Sys J"},{"key":"118_CR22","unstructured":"Frean GBM, Noble J, Rickerby M, Smith H, Visser M, Melton H, Tempero E (2006) Understanding the shape of java software. In: OOPSLA \u201906. ACM Press, New York, pp 397\u2013503"},{"key":"118_CR23","doi-asserted-by":"crossref","unstructured":"Gil JY, Maman I (2005) Micro patterns in java code. In: OOPSLA \u201905: proceedings of the 20th annual ACM SIGPLAN conference on object oriented programming systems languages and applications. ACM Press, New York, pp 97\u2013116","DOI":"10.1145\/1094811.1094819"},{"issue":"Suppl 1","key":"118_CR24","doi-asserted-by":"crossref","first-page":"5228","DOI":"10.1073\/pnas.0307752101","volume":"101","author":"TL Griffiths","year":"2004","unstructured":"Griffiths TL, Steyvers M (2004) Finding scientific topics. Proc Natl Acad Sci U S A 101(Suppl 1): 5228\u20135235","journal-title":"Proc Natl Acad Sci U S A"},{"key":"118_CR25","first-page":"2","volume-title":"ECOOP\u201906: proceedings of the 20th European conference on object-oriented programming, vol 4067 of lecture notes in computer science","author":"E Hajiyev","year":"2006","unstructured":"Hajiyev E, Verbaere M, de Moor O (2006) Codequest: scalable source code queries with datalog. In: Thomas D (eds) ECOOP\u201906: proceedings of the 20th European conference on object-oriented programming, vol 4067 of lecture notes in computer science. Springer, Berlin, pp 2\u201327"},{"key":"118_CR26","doi-asserted-by":"crossref","unstructured":"Hill R, Rideout J (2004) Automatic method completion. In: ASE. IEEE Computer Society, pp 228\u2013235","DOI":"10.1109\/ASE.2004.1342740"},{"key":"118_CR27","doi-asserted-by":"crossref","unstructured":"Holmes R, Murphy GC (2005) Using structural context to recommend source code examples. In: ICSE \u201905: proceedings of the 27th international conference on software engineering. ACM Press, New York, pp 117\u2013125","DOI":"10.1145\/1062455.1062491"},{"issue":"12","key":"118_CR28","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1109\/TSE.2006.117","volume":"32","author":"R Holmes","year":"2006","unstructured":"Holmes R, Walker RJ, Murphy GC (2006) Approximate structural context matching: an approach to recommend relevant examples. IEEE Trans Softw Eng 32(12): 952\u2013970","journal-title":"IEEE Trans Softw Eng"},{"key":"118_CR29","doi-asserted-by":"crossref","unstructured":"Inoue K, Yokomori R, Fujiwara H, Yamamoto T, Matsushita M, Kusumoto S (2003) Component rank: relative significance rank for software component search. In: ICSE \u201903: proceedings of the 25th international conference on software engineering. IEEE Computer Society, Washington, DC, pp 14\u201324","DOI":"10.1109\/ICSE.2003.1201184"},{"issue":"3","key":"118_CR30","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1109\/TSE.2005.38","volume":"31","author":"K Inoue","year":"2005","unstructured":"Inoue K, Yokomori R, Yamamoto T, Kusumoto S (2005) Ranking significance of software components based on use relations. IEEE Trans Softw Eng 31(3): 213\u2013225","journal-title":"IEEE Trans Softw Eng"},{"key":"118_CR31","doi-asserted-by":"crossref","unstructured":"Kawaguchi S, Garg PK, Matsushita M, Inoue K (2004) Mudablue: an automatic categorization system for open source repositories. In: APSEC \u201904: proceedings of the 11th Asia-Pacific software engineering conference (APSEC\u201904). IEEE Computer Society, Washington, DC, pp 184\u2013193","DOI":"10.1109\/APSEC.2004.69"},{"key":"118_CR32","first-page":"220","volume-title":"Proceedings European conference on object-oriented programming, vol 1241","author":"G Kiczales","year":"1997","unstructured":"Kiczales G, Lamping J, Menhdhekar A, Maeda C, Lopes C, Loingtier J, Irwin J (1997) Aspect-oriented programming. In: Ak\u015fit M, Matsuoka S (eds) Proceedings European conference on object-oriented programming, vol 1241. Springer, Berlin, pp 220\u2013242"},{"issue":"2","key":"118_CR33","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1002\/spe.4380010203","volume":"1","author":"DE Knuth","year":"1971","unstructured":"Knuth DE (1971) An empirical study of fortran programs. Softw Pract Exp 1(2):105\u2013133","journal-title":"Softw Pract Exp"},{"issue":"3","key":"118_CR34","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.infsof.2006.10.017","volume":"49","author":"A Kuhn","year":"2007","unstructured":"Kuhn A, Ducasse S, G\u00edrba T (2007) Semantic clustering: identifying topics in source code. Info Softw Technol 49(3): 230\u2013243","journal-title":"Info Softw Technol"},{"key":"118_CR35","doi-asserted-by":"crossref","unstructured":"Linstead E, Rigor P, Bajracharya S, Lopes C, Baldi P (2007) Mining eclipse developer contributions via author-topic models. MSR 2007: proceedings of the fourth international workshop on mining software repositories. pp 30\u201333","DOI":"10.1109\/MSR.2007.20"},{"key":"118_CR36","first-page":"929","volume-title":"Advances in neural information processing systems, vol 20","author":"E Linstead","year":"2008","unstructured":"Linstead E, Rigor P, Bajracharya S, Lopes C, Baldi P (2008) Mining internet-scale software repositories. In: Platt JC, Koller D, Singer Y, Roweis S (eds) Advances in neural information processing systems, vol 20. MIT Press, Cambridge, MA, pp 929\u2013936"},{"key":"118_CR37","doi-asserted-by":"crossref","unstructured":"Liu C, Chen C, Han J, Yu PS (2006) Gplag: detection of software plagiarism by program dependence graph analysis. In: KDD \u201906: proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, New York, pp 872\u2013881","DOI":"10.1145\/1150402.1150522"},{"key":"118_CR38","doi-asserted-by":"crossref","unstructured":"Mandelin D, Xu L, Bod\u00edk R, Kimelman D (2005) Jungloid mining: helping to navigate the api jungle. In: PLDI \u201905: proceedings of the 2005 ACM SIGPLAN conference on programming language design and implementation. ACM Press, New York, pp 48\u201361","DOI":"10.1145\/1065010.1065018"},{"key":"118_CR39","doi-asserted-by":"crossref","unstructured":"Marcus A, Sergeyev A, Rajlich V, Maletic J (2004) An information retrieval approach to concept location in source code. In: Proceedings of the 11th working conference on reverse engineering (WCRE 2004). The Netherlands, pp 214\u2013223","DOI":"10.1109\/WCRE.2004.10"},{"key":"118_CR40","doi-asserted-by":"crossref","unstructured":"McCormick E, Volder KD (2004) Jquery: finding your way through tangled code. In: OOPSLA \u201904: companion to the 19th annual ACM SIGPLAN conference on object-oriented programming systems, languages, and applications. ACM. New York, pp 9\u201310","DOI":"10.1145\/1028664.1028670"},{"key":"118_CR41","doi-asserted-by":"crossref","unstructured":"Minto S, Murphy GC (2007) Recommending emergent teams. In: MSR \u201907: proceedings of the fourth international workshop on mining software repositories. IEEE Computer Society. Washington, DC, p 5","DOI":"10.1109\/MSR.2007.27"},{"key":"118_CR42","doi-asserted-by":"crossref","unstructured":"Mitzenmacher, M. (2003) A brief history of generative models for power law and lognormal distributions. Internet Math 1(2)","DOI":"10.1080\/15427951.2004.10129088"},{"issue":"1","key":"118_CR43","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1145\/375360.375365","volume":"33","author":"G Navarro","year":"2001","unstructured":"Navarro G (2001) A guided tour to approximate string matching. ACM Comput Surv 33(1):31\u201388","journal-title":"ACM Comput Surv"},{"issue":"6","key":"118_CR44","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1002\/asi.20342","volume":"57","author":"D Newman","year":"2006","unstructured":"Newman D, Block S (2006) Probabilistic topic decomposition of an eighteenth-century american newspaper. J Am Soc Inf Sci Technol 57(6): 753\u2013767","journal-title":"J Am Soc Inf Sci Technol"},{"key":"118_CR45","doi-asserted-by":"crossref","unstructured":"Newman D, Chemudugunta C, Smyth P, Steyvers M (2006) Analyzing entities and topics in news articles using statistical topic models. In: ISI. pp 93\u2013104","DOI":"10.1007\/11760146_9"},{"key":"118_CR46","doi-asserted-by":"crossref","unstructured":"Oman P, Hagemeister J (1992) Metrics for assessing a software system\u2019s maintainability. In: Proceedings of the international conference on software maintenance 1992. IEEE Computer Society Press, pp 337\u2013344","DOI":"10.1109\/ICSM.1992.242525"},{"key":"118_CR47","unstructured":"Page L, Brin S, Motwani R, Winograd T (1998) The pagerank citation ranking: bringing order to the web. Stanford Digital Library working paper SIDL-WP-1999-0120 of 11\/11\/1999 (see: http:\/\/dbpubs.stanford.edu\/pub\/1999-66 )"},{"key":"118_CR48","unstructured":"Paul S (1992) Scruple: a reengineer\u2019s tool for source code search. In: CASCON \u201992: proceedings of the 1992 conference of the centre for advanced studies on collaborative research. IBM Press, pp 329\u2013346"},{"issue":"6","key":"118_CR49","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1109\/32.295894","volume":"20","author":"S Paul","year":"1994","unstructured":"Paul S, Prakash A (1994) A framework for source code search using program patterns. IEEE Trans Softw Eng 20(6): 463\u2013475","journal-title":"IEEE Trans Softw Eng"},{"key":"118_CR50","first-page":"252","volume":"0","author":"D Poshyvanyk","year":"2006","unstructured":"Poshyvanyk D, Marcus A, Dong Y (2006) Jiriss\u2014an eclipse plug-in for source code exploration. ICPC 0: 252\u2013255","journal-title":"ICPC"},{"key":"118_CR51","doi-asserted-by":"crossref","unstructured":"Puppin D, Silvestri F (2006) The social network of java classes. In: Haddad H (ed) SAC. ACM, New York, pp 1409\u20131413","DOI":"10.1145\/1141277.1141605"},{"key":"118_CR52","unstructured":"Rosen-Zvi M, Griffiths T, Steyvers M, Smyth P (2004) The author-topic model for authors and documents. In: UAI \u201904: proceedings of the 20th conference on uncertainty in artificial intelligence. AUAI Press, Arlington, pp 487\u2013494"},{"issue":"10","key":"118_CR53","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1145\/1167515.1167508","volume":"41","author":"N Sahavechaphan","year":"2006","unstructured":"Sahavechaphan N, Claypool K (2006) Xsnippet: mining for sample code. SIGPLAN Not 41(10): 413\u2013430","journal-title":"SIGPLAN Not"},{"key":"118_CR54","doi-asserted-by":"crossref","unstructured":"Schleimer S, Wilkerson DS, Aiken A (2003) Winnowing: local algorithms for document fingerprinting. In: SIGMOD \u201903: proceedings of the 2003 ACM SIGMOD international conference on management of data. ACM, New York, pp 76\u201385","DOI":"10.1145\/872757.872770"},{"key":"118_CR55","unstructured":"Schr\u00f6ter A, Zimmermann T, Premraj R, Zeller A (2006) If your bug database could talk .... In: Proceedings of the 5th international symposium on empirical software engineering, vol II: short papers and posters. Rio de Janeiro, pp 18\u201320"},{"key":"118_CR56","doi-asserted-by":"crossref","unstructured":"Sindhgatta R (2006) Using an information retrieval system to retrieve source code samples. In: Osterweil LJ, Rombach HD, Soffa ML, (eds) ICSE. ACM, pp 905\u2013908","DOI":"10.1145\/1134285.1134448"},{"key":"118_CR57","doi-asserted-by":"crossref","unstructured":"Steyvers M, Smyth P, Rosen-Zvi M, Griffiths T (2004) Probabilistic author-topic models for information discovery. In: KDD \u201904: proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM Press, New York, pp 306\u2013315","DOI":"10.1145\/1014052.1014087"},{"issue":"2","key":"118_CR58","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1021\/ci600358f","volume":"47","author":"S Swamidass","year":"2007","unstructured":"Swamidass S, Baldi P (2007) Bounds and algorithms for exact searches of chemical fingerprints in linear and sub-linear time. J Chem Inf Model 47(2): 302\u2013317","journal-title":"J Chem Inf Model"},{"issue":"476","key":"118_CR59","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1198\/016214506000000302","volume":"101","author":"YW Teh","year":"2006","unstructured":"Teh YW, Jordan MI, Beal MJ, Blei DM (2006) Hierarchical Dirichlet processes. J Am Statistical Assoc 101(476): 1566\u20131581","journal-title":"J Am Statistical Assoc"},{"key":"118_CR60","doi-asserted-by":"crossref","unstructured":"Ugurel S, Krovetz R, Giles CL (2002) What\u2019s the code? automatic classification of source code archives. In: KDD \u201902: proceedings of the eighth ACM SIGKDD international conference on knowledge discovery and data mining. ACM Press, New York, pp 632\u2013638","DOI":"10.1145\/775047.775141"},{"issue":"1","key":"118_CR61","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/0304-3975(92)90143-4","volume":"92","author":"E Ukkonen","year":"1992","unstructured":"Ukkonen E (1992) Approximate string-matching with q-grams and maximal matches. Theor Comput Sci 92(1): 191\u2013211","journal-title":"Theor Comput Sci"},{"key":"118_CR62","first-page":"19","volume":"8","author":"KD Welker","year":"1995","unstructured":"Welker KD, Oman PW (1995) Software maintainability metrics models in practice. Crosstalk, J Def Softw Eng 8: 19\u201323","journal-title":"Crosstalk, J Def Softw Eng"},{"key":"118_CR63","doi-asserted-by":"crossref","unstructured":"Wheeldon R, Counsell S (2003) Power law distributions in class relationships. In: International workshop on source code analysis and manipulation, pp 45\u201354","DOI":"10.1109\/SCAM.2003.1238030"},{"key":"118_CR64","doi-asserted-by":"crossref","unstructured":"Ye Y, Fischer G (2002) Supporting reuse by delivering task-relevant and personalized information. In: ICSE \u201902: proceedings of the 24th international conference on software engineering. ACM, New York, pp 513\u2013523","DOI":"10.1145\/581339.581402"},{"key":"118_CR65","doi-asserted-by":"crossref","unstructured":"Zipf GK (1932) Selective studies and the principle of relative frequency in language. Harvard University Press","DOI":"10.4159\/harvard.9780674434929"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-008-0118-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10618-008-0118-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-008-0118-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T19:29:40Z","timestamp":1559244580000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10618-008-0118-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,10,15]]},"references-count":65,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2009,4]]}},"alternative-id":["118"],"URL":"https:\/\/doi.org\/10.1007\/s10618-008-0118-x","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,10,15]]}}}