{"id":"https://openalex.org/W2007022086","doi":"https://doi.org/10.1109/icpc.2012.6240488","title":"Using IR methods for labeling source code artifacts: Is it worthwhile?","display_name":"Using IR methods for labeling source code artifacts: Is it worthwhile?","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2007022086","doi":"https://doi.org/10.1109/icpc.2012.6240488","mag":"2007022086"},"language":"en","primary_location":{"id":"doi:10.1109/icpc.2012.6240488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpc.2012.6240488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 20th IEEE International Conference on Program Comprehension (ICPC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5079088548","display_name":"Andrea De Lucia","orcid":"https://orcid.org/0000-0002-4238-1425"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea De Lucia","raw_affiliation_strings":["University of Salerno, Fisciano, Salerno, Italy","University of Salerno, Via Ponte Don Melillo, 84084 Fisciano (SA), Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Salerno, Fisciano, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"University of Salerno, Via Ponte Don Melillo, 84084 Fisciano (SA), Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025099559","display_name":"Massimiliano Di Penta","orcid":"https://orcid.org/0000-0002-0340-9747"},"institutions":[{"id":"https://openalex.org/I16337185","display_name":"University of Sannio","ror":"https://ror.org/04vc81p87","country_code":"IT","type":"education","lineage":["https://openalex.org/I16337185"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimiliano Di Penta","raw_affiliation_strings":["University of Sannio, Benevento, Italy","University of Sannio, Viale Traiano - 82100 Benevento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sannio, Benevento, Italy","institution_ids":["https://openalex.org/I16337185"]},{"raw_affiliation_string":"University of Sannio, Viale Traiano - 82100 Benevento, Italy","institution_ids":["https://openalex.org/I16337185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009727039","display_name":"Rocco Oliveto","orcid":"https://orcid.org/0000-0002-7995-8582"},"institutions":[{"id":"https://openalex.org/I129627893","display_name":"University of Molise","ror":"https://ror.org/04z08z627","country_code":"IT","type":"education","lineage":["https://openalex.org/I129627893"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rocco Oliveto","raw_affiliation_strings":["University of Molise, Pesche, Italy","University of Molise, C.da Fonte Lappone - 86090 Pesche (IS), Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Molise, Pesche, Italy","institution_ids":["https://openalex.org/I129627893"]},{"raw_affiliation_string":"University of Molise, C.da Fonte Lappone - 86090 Pesche (IS), Italy","institution_ids":["https://openalex.org/I129627893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067127346","display_name":"Annibale Panichella","orcid":"https://orcid.org/0000-0002-7395-3588"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Annibale Panichella","raw_affiliation_strings":["University of Salerno, Fisciano, Salerno, Italy","University of Salerno, Via Ponte Don Melillo, 84084 Fisciano (SA), Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Salerno, Fisciano, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"University of Salerno, Via Ponte Don Melillo, 84084 Fisciano (SA), Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063227479","display_name":"Sebastiano Panichella","orcid":"https://orcid.org/0000-0003-4120-626X"},"institutions":[{"id":"https://openalex.org/I16337185","display_name":"University of Sannio","ror":"https://ror.org/04vc81p87","country_code":"IT","type":"education","lineage":["https://openalex.org/I16337185"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sebastiano Panichella","raw_affiliation_strings":["University of Sannio, Benevento, Italy","University of Sannio, Viale Traiano - 82100 Benevento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sannio, Benevento, Italy","institution_ids":["https://openalex.org/I16337185"]},{"raw_affiliation_string":"University of Sannio, Viale Traiano - 82100 Benevento, Italy","institution_ids":["https://openalex.org/I16337185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"202"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9932000041007996,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8335038423538208},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7140417098999023},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6520856618881226},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6095073223114014},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.5811932682991028},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5538048148155212},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5305110812187195},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.4951883852481842},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4875352084636688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4777492880821228},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.44016045331954956},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.413827121257782},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3852134048938751},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33303725719451904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3247906565666199},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.320407509803772},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.2920299172401428},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25171273946762085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335038423538208},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7140417098999023},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6520856618881226},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6095073223114014},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.5811932682991028},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5538048148155212},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5305110812187195},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.4951883852481842},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4875352084636688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4777492880821228},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.44016045331954956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.413827121257782},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3852134048938751},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33303725719451904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3247906565666199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.320407509803772},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2920299172401428},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25171273946762085},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpc.2012.6240488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpc.2012.6240488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 20th IEEE International Conference on Program Comprehension (ICPC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1244965290","https://openalex.org/W1447066968","https://openalex.org/W1553570763","https://openalex.org/W1660390307","https://openalex.org/W1880262756","https://openalex.org/W1928657940","https://openalex.org/W1972886276","https://openalex.org/W1980357388","https://openalex.org/W1991945471","https://openalex.org/W1996225375","https://openalex.org/W2054805201","https://openalex.org/W2057049321","https://openalex.org/W2082160726","https://openalex.org/W2098162425","https://openalex.org/W2108036122","https://openalex.org/W2109144580","https://openalex.org/W2110374486","https://openalex.org/W2111643214","https://openalex.org/W2118202700","https://openalex.org/W2119070456","https://openalex.org/W2120275495","https://openalex.org/W2120589327","https://openalex.org/W2122987719","https://openalex.org/W2123551785","https://openalex.org/W2124672527","https://openalex.org/W2127929486","https://openalex.org/W2128581098","https://openalex.org/W2130997088","https://openalex.org/W2133333349","https://openalex.org/W2136296681","https://openalex.org/W2138378644","https://openalex.org/W2139543149","https://openalex.org/W2140264852","https://openalex.org/W2143818143","https://openalex.org/W2146781646","https://openalex.org/W2147152072","https://openalex.org/W2148429572","https://openalex.org/W2154880989","https://openalex.org/W2163724607","https://openalex.org/W2163960678","https://openalex.org/W2164233915","https://openalex.org/W2166879716","https://openalex.org/W2793679191","https://openalex.org/W3106006586","https://openalex.org/W4237791300","https://openalex.org/W4241755296","https://openalex.org/W4251218026"],"related_works":["https://openalex.org/W3107650560","https://openalex.org/W3126382579","https://openalex.org/W4317422773","https://openalex.org/W4315588616","https://openalex.org/W2810542905","https://openalex.org/W3123667230","https://openalex.org/W4243064001","https://openalex.org/W2129350855","https://openalex.org/W2888805565","https://openalex.org/W3096554474"],"abstract_inverted_index":{"Information":[0],"Retrieval":[1],"(IR)":[2],"techniques":[3,24,58,108],"have":[4],"been":[5,70],"used":[6,137],"for":[7,149],"various":[8],"software":[9,16,85],"engineering":[10],"tasks,":[11],"including":[12],"the":[13],"labeling":[14,54,64,97,104],"of":[15,76],"artifacts":[17,141,150],"by":[18,56,66,72],"extracting":[19,40],"\u201ckeywords\u201d":[20],"from":[21,42,63,82,113],"them.":[22],"Such":[23],"include":[25],"Vector":[26],"Space":[27],"Models,":[28],"Latent":[29,32],"Semantic":[30],"Indexing,":[31],"Dirichlet":[33],"Allocation,":[34],"as":[35,37,146,148],"well":[36,147],"customized":[38],"heuristics":[39],"words":[41,112],"specific":[43],"source":[44,51,139],"code":[45,52,140],"elements.":[46],"This":[47,68],"paper":[48],"investigates":[49],"how":[50,122],"artifact":[53],"performed":[55,65],"IR":[57],"would":[59,98],"overlap":[60],"(and":[61],"differ)":[62],"humans.":[67],"has":[69],"done":[71],"asking":[73],"a":[74,143],"group":[75],"subjects":[77],"to":[78,102,135,154],"label":[79],"20":[80],"classes":[81],"two":[83],"Java":[84],"systems,":[86],"JHotDraw":[87],"and":[88,115,129],"eXVantage.":[89],"Results":[90],"indicate":[91],"that,":[92],"in":[93],"most":[94],"cases,":[95],"automatic":[96],"be":[99,136,155],"more":[100,133,152],"similar":[101],"human-based":[103],"if":[105],"using":[106,111],"simpler":[107],"\u2014":[109,118],"e.g.,":[110],"class":[114],"method":[116],"names":[117],"that":[119],"better":[120],"reflect":[121],"humans":[123],"behave.":[124],"Instead,":[125],"clustering-based":[126],"approaches":[127],"(LSI":[128],"LDA)":[130],"are":[131],"much":[132],"worthwhile":[134],"on":[138],"having":[142],"high":[144],"verbosity,":[145],"requiring":[151],"effort":[153],"manually":[156],"labeled.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}