{"id":"https://openalex.org/W2128737833","doi":"https://doi.org/10.1109/msr.2009.5069482","title":"Mining source code to automatically split identifiers for software analysis","display_name":"Mining source code to automatically split identifiers for software analysis","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2128737833","doi":"https://doi.org/10.1109/msr.2009.5069482","mag":"2128737833"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2009.5069482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 6th IEEE International Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061087381","display_name":"Eric Enslen","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eric Enslen","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Delaware, Newark, DE, USA","Department of Computer and Information Sciences, University of Delaware, Newark 19716, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark 19716, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000817140","display_name":"Emily Hill","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Hill","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Delaware, Newark, DE, USA","Department of Computer and Information Sciences, University of Delaware, Newark 19716, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark 19716, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068927917","display_name":"Lori Pollock","orcid":"https://orcid.org/0000-0002-4388-4892"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lori Pollock","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Delaware, Newark, DE, USA","Department of Computer and Information Sciences, University of Delaware, Newark 19716, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark 19716, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027009667","display_name":"K. Vijay\u2010Shanker","orcid":"https://orcid.org/0000-0003-0958-3073"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Vijay-Shanker","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Delaware, Newark, DE, USA","Department of Computer and Information Sciences, University of Delaware, Newark 19716, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark 19716, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061087381"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":37.1874,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.99684042,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.9667141437530518},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8724616169929504},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5783809423446655},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5649309754371643},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5095882415771484},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4946891963481903},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.45816072821617126},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4523910880088806},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4255509078502655},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4163852334022522},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37022340297698975},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.20241427421569824},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.11772677302360535}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.9667141437530518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8724616169929504},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5783809423446655},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5649309754371643},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5095882415771484},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4946891963481903},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.45816072821617126},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4523910880088806},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4255509078502655},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4163852334022522},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37022340297698975},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.20241427421569824},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.11772677302360535},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/msr.2009.5069482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 6th IEEE International Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.2737","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.2737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.471.6987","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.471.6987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://flosshub.org/sites/flosshub.org/files/71EnslenandHillandPollockandVijayShanker.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W188027806","https://openalex.org/W2010981136","https://openalex.org/W2012313588","https://openalex.org/W2041853131","https://openalex.org/W2045922551","https://openalex.org/W2077155146","https://openalex.org/W2079317829","https://openalex.org/W2097403040","https://openalex.org/W2109144580","https://openalex.org/W2110220994","https://openalex.org/W2111909698","https://openalex.org/W2119109877","https://openalex.org/W2121455545","https://openalex.org/W2125480321","https://openalex.org/W2127577307","https://openalex.org/W2128581098","https://openalex.org/W2130333788","https://openalex.org/W2144517582","https://openalex.org/W2147751596","https://openalex.org/W2149938198","https://openalex.org/W2157791244","https://openalex.org/W2157836986","https://openalex.org/W2163724607","https://openalex.org/W2165022036","https://openalex.org/W2171238733","https://openalex.org/W2171733741","https://openalex.org/W3143277278","https://openalex.org/W4241947741","https://openalex.org/W4251218026","https://openalex.org/W6676560868","https://openalex.org/W6681198100"],"related_works":["https://openalex.org/W2099969795","https://openalex.org/W3120493416","https://openalex.org/W2098192829","https://openalex.org/W377327559","https://openalex.org/W4210653322","https://openalex.org/W3029691491","https://openalex.org/W4206152185","https://openalex.org/W2969257295","https://openalex.org/W1976804602","https://openalex.org/W4245904369"],"abstract_inverted_index":{"Automated":[0],"software":[1],"engineering":[2],"tools":[3],"(e.g.,":[4],"program":[5],"search,":[6],"concern":[7],"location,":[8],"code":[9],"reuse,":[10],"quality":[11],"assessment,":[12],"etc.)":[13],"increasingly":[14],"rely":[15],"on":[16],"natural":[17,42],"language":[18,67],"information":[19],"from":[20,32,160],"comments":[21],"and":[22,46],"identifiers":[23,33,36,53,62,92,120,159],"in":[24,29,129],"code.":[25,131],"The":[26],"first":[27],"step":[28],"analyzing":[30],"words":[31,79,97,124],"requires":[34],"splitting":[35],"into":[37,121],"their":[38],"constituent":[39],"words.":[40],"Unlike":[41],"languages,":[43],"where":[44,78],"space":[45],"punctuation":[47],"are":[48,80],"used":[49],"to":[50,60,64,106,117,143],"delineate":[51],"words,":[52],"cannot":[54],"contain":[55],"spaces.":[56],"One":[57],"common":[58],"way":[59],"split":[61,119],"is":[63],"follow":[65],"programming":[66],"naming":[68],"conventions.":[69],"For":[70],"example,":[71],"Java":[72,163],"programmers":[73,89],"often":[74],"use":[75],"camel":[76],"case,":[77],"delineated":[81],"by":[82,93,125],"uppercase":[83],"letters":[84],"or":[85],"non-alphabetic":[86],"characters.":[87],"However,":[88],"also":[90],"create":[91],"concatenating":[94],"sequences":[95,122],"of":[96,123,156,172],"together":[98],"with":[99],"no":[100],"discernible":[101],"delineation,":[102],"which":[103],"poses":[104],"challenges":[105],"automatic":[107],"identifier":[108,137],"splitting.":[109],"In":[110,153],"this":[111],"paper,":[112],"we":[113],"present":[114],"an":[115,151,154],"algorithm":[116],"automatically":[118,144],"mining":[126],"word":[127,134],"frequencies":[128],"source":[130,162],"With":[132],"these":[133],"frequencies,":[135],"our":[136,165],"splitter":[138],"uses":[139],"a":[140],"scoring":[141],"technique":[142],"select":[145],"the":[146,169,173],"most":[147],"appropriate":[148],"partitioning":[149],"for":[150],"identifier.":[152],"evaluation":[155],"over":[157],"8000":[158],"open":[161],"programs,":[164],"Samurai":[166],"approach":[167],"outperforms":[168],"existing":[170],"state":[171],"art":[174],"techniques.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":22}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}