{"id":"https://openalex.org/W2109099384","doi":"https://doi.org/10.1109/icsm.2015.7332491","title":"Is this code written in English? A study of the natural language of comments and identifiers in practice","display_name":"Is this code written in English? A study of the natural language of comments and identifiers in practice","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2109099384","doi":"https://doi.org/10.1109/icsm.2015.7332491","mag":"2109099384"},"language":"en","primary_location":{"id":"doi:10.1109/icsm.2015.7332491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsm.2015.7332491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Software Maintenance and Evolution (ICSME)","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/A5032593963","display_name":"Timo Pawelka","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Timo Pawelka","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen","Technische Universitat, Munchen, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technische Universitat, Munchen, Germany#TAB#","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085630369","display_name":"Elmar Juergens","orcid":"https://orcid.org/0000-0003-1692-6839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elmar Juergens","raw_affiliation_strings":["CQSE GmbH, Garching b, M\u00fcnchen, Germany","CQSE GmbH, Garching b. M\u00fcnchen, Germany"],"affiliations":[{"raw_affiliation_string":"CQSE GmbH, Garching b, M\u00fcnchen, Germany","institution_ids":[]},{"raw_affiliation_string":"CQSE GmbH, Garching b. M\u00fcnchen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032593963"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.6468,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88251243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"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":0.9997000098228455,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9965000152587891,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9857000112533569,"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":0.959084153175354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8269400000572205},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6623696088790894},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.6455455422401428},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6125478148460388},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5159490704536438},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.508875846862793},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.49318593740463257},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48090672492980957},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.45088067650794983},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43545156717300415},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.41727888584136963},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.26660969853401184},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09602943062782288}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.959084153175354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269400000572205},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6623696088790894},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6455455422401428},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6125478148460388},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5159490704536438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.508875846862793},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.49318593740463257},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48090672492980957},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.45088067650794983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43545156717300415},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.41727888584136963},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26660969853401184},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09602943062782288},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icsm.2015.7332491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsm.2015.7332491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Software Maintenance and Evolution (ICSME)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.1038","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.1038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.cqse.eu/publications/2015-is-this-code-written-in-english-a-study-of-the-natural-language-of-comments-and-identifiers-in-practice.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W68251067","https://openalex.org/W92274471","https://openalex.org/W1490674333","https://openalex.org/W1533946607","https://openalex.org/W1558954385","https://openalex.org/W1598996557","https://openalex.org/W1791687657","https://openalex.org/W1951381097","https://openalex.org/W2039603939","https://openalex.org/W2070111972","https://openalex.org/W2077155146","https://openalex.org/W2133890582","https://openalex.org/W2147296306","https://openalex.org/W2164886519","https://openalex.org/W2169200297","https://openalex.org/W2170505850","https://openalex.org/W2183864645","https://openalex.org/W4213138647","https://openalex.org/W6603742028","https://openalex.org/W6629329164","https://openalex.org/W6632118081","https://openalex.org/W6633414044","https://openalex.org/W6640788013","https://openalex.org/W6660297481","https://openalex.org/W6684503276"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2343500026","https://openalex.org/W2319837024","https://openalex.org/W2390627310","https://openalex.org/W2413664130","https://openalex.org/W2051731675","https://openalex.org/W2033159440"],"abstract_inverted_index":{"Comments":[0],"and":[1,11,20,34,84,102,120,125,141],"identifiers":[2,35,85,142],"are":[3,12,36,43],"the":[4,18,21,29,58,76,79,96,105,114,136,151],"main":[5],"source":[6],"of":[7,9,17,23,52,68,75,78,81,99,113,117,135,150],"documentation":[8],"source-code":[10,100,118],"therefore":[13],"an":[14,93],"integral":[15],"part":[16],"development":[19],"maintenance":[22],"a":[24,48,107,132],"program.":[25],"As":[26],"English":[27],"is":[28,72],"world":[30],"language,":[31,47,147],"most":[32],"comments":[33,83,101,119,140],"written":[37],"in":[38,44,86,143],"English.":[39],"However,":[40],"if":[41],"they":[42],"any":[45],"other":[46],"developer":[49],"without":[50],"knowledge":[51],"this":[53,89,156],"language":[54,97,116],"will":[55],"almost":[56],"perceive":[57],"code":[59],"to":[60],"be":[61],"undocumented":[62],"or":[63],"even":[64],"obfuscated.":[65],"In":[66,88],"absence":[67],"industrial":[69],"data,":[70],"academia":[71],"not":[73],"aware":[74],"extent":[77],"problem":[80],"non-English":[82],"practice.":[87],"paper,":[90],"we":[91],"propose":[92],"approach":[94],"for":[95],"identification":[98],"identifiers.":[103],"With":[104],"approach,":[106],"large-scale":[108],"study":[109],"has":[110,155],"been":[111],"conducted":[112],"natural":[115],"identifiers,":[121],"analyzing":[122],"multiple":[123],"open-source":[124,153],"industry":[126,137],"systems.":[127],"The":[128],"results":[129],"show":[130],"that":[131],"significant":[133],"amount":[134],"projects":[138],"contain":[139],"more":[144],"than":[145],"one":[146],"whereas":[148],"none":[149],"analyzed":[152],"systems":[154],"problem.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
