{"id":"https://openalex.org/W2114763031","doi":"https://doi.org/10.1109/msr.2009.5069499","title":"Automatic labeling of software components and their evolution using log-likelihood ratio of word frequencies in source code","display_name":"Automatic labeling of software components and their evolution using log-likelihood ratio of word frequencies in source code","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2114763031","doi":"https://doi.org/10.1109/msr.2009.5069499","mag":"2114763031"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2009.5069499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069499","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/A5036425716","display_name":"Adrian Kuhn","orcid":null},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Adrian Kuhn","raw_affiliation_strings":["Software Composition Group, University of Bern, Switzerland","Software Composition Group, University of Bern, Switzerland#TAB#"],"affiliations":[{"raw_affiliation_string":"Software Composition Group, University of Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]},{"raw_affiliation_string":"Software Composition Group, University of Bern, Switzerland#TAB#","institution_ids":["https://openalex.org/I118564535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036425716"],"corresponding_institution_ids":["https://openalex.org/I118564535"],"apc_list":null,"apc_paid":null,"fwci":9.3156,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.97753058,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"49","issue":null,"first_page":"175","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9962999820709229,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.8230413198471069},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.7278124094009399},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5982711315155029},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5408329367637634},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.508564829826355},{"id":"https://openalex.org/keywords/kpi-driven-code-analysis","display_name":"KPI-driven code analysis","score":0.4605729579925537},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.45025742053985596},{"id":"https://openalex.org/keywords/open-source-software","display_name":"Open source software","score":0.41998153924942017},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.371563196182251},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3476569354534149},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.3179404139518738},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28720152378082275},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08617982268333435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230413198471069},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7278124094009399},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5982711315155029},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5408329367637634},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.508564829826355},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.4605729579925537},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.45025742053985596},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.41998153924942017},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.371563196182251},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3476569354534149},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3179404139518738},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28720152378082275},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08617982268333435},{"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.2009.5069499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069499","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:10.1.1.150.3829","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.3829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://scg.unibe.ch/archive/papers/Kuhn09aLogLikelihoodRatio.pdf","raw_type":"text"},{"id":"pmh:oai:boris.unibe.ch:37152","is_oa":false,"landing_page_url":"https://boris.unibe.ch/37152/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401086","display_name":"Bern Open Repository and Information System (University of Bern)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118564535","host_organization_name":"University of Bern","host_organization_lineage":["https://openalex.org/I118564535"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kuhn, Adrian (2009). Automatic Labeling of Software Components and their Evolution using Log-Likelihood Ratio of Word Frequencies in Source Code. In: Proceedings of the 2009 6th IEEE International Working Conference on Mining Software Repositories, 16-17 May 2009, Vancouver BC (pp. 175-178). Washington, DC: IEEE Computer Society 10.1109/MSR.2009.5069499 &lt;http://dx.doi.org/10.1109/MSR.2009.5069499&gt;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1575800506","https://openalex.org/W1612003148","https://openalex.org/W1928731475","https://openalex.org/W1991945471","https://openalex.org/W1997885138","https://openalex.org/W2018783607","https://openalex.org/W2060704087","https://openalex.org/W2066651136","https://openalex.org/W2101414596","https://openalex.org/W2109144580","https://openalex.org/W2114708302","https://openalex.org/W2116780029","https://openalex.org/W2126551897","https://openalex.org/W2162982974","https://openalex.org/W2163960678","https://openalex.org/W2164233915","https://openalex.org/W3099904688","https://openalex.org/W4251218026","https://openalex.org/W6677145740"],"related_works":["https://openalex.org/W2113128227","https://openalex.org/W2491403535","https://openalex.org/W377327559","https://openalex.org/W4210653322","https://openalex.org/W632256878","https://openalex.org/W2104915799","https://openalex.org/W1976804602","https://openalex.org/W2316077753","https://openalex.org/W4311938462","https://openalex.org/W3006945192"],"abstract_inverted_index":{"As":[0],"more":[1,3],"and":[2,18,60,96],"open-source":[4],"software":[5,29,85,116],"components":[6],"become":[7],"available":[8],"on":[9],"the":[10,47,54,61,74,106,112],"Internet":[11],"we":[12,67,104],"need":[13],"automatic":[14],"ways":[15],"to":[16,33,53,80,108],"label":[17],"compare":[19],"them.":[20],"For":[21],"example,":[22],"a":[23,69,89,115],"developer":[24],"who":[25],"searches":[26],"for":[27,84],"reusable":[28],"must":[30],"be":[31,44],"able":[32],"quickly":[34],"gain":[35],"an":[36],"understanding":[37,42],"of":[38,49,77,92,99,114],"retrieved":[39],"components.":[40,86],"This":[41],"cannot":[43],"gained":[45],"at":[46],"level":[48],"source":[50,58],"code":[51,59],"due":[52],"semantic":[55],"gap":[56],"between":[57],"domain":[62],"model.":[63],"In":[64,102],"this":[65],"paper":[66],"present":[68,88],"lexical":[70],"approach":[71,107],"that":[72],"uses":[73],"log-likelihood":[75],"ratios":[76],"word":[78],"frequencies":[79],"automatically":[81],"provide":[82,97],"labels":[83],"We":[87],"prototype":[90],"implementation":[91],"our":[93],"labeling/comparison":[94],"algorithm":[95],"examples":[98],"its":[100],"application.":[101],"particular,":[103],"apply":[105],"detect":[109],"trends":[110],"in":[111],"evolution":[113],"system.":[117]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
