{"id":"https://openalex.org/W1965876361","doi":"https://doi.org/10.1109/icsm.2012.6405328","title":"Vocabulary normalization improves IR-based concept location","display_name":"Vocabulary normalization improves IR-based concept location","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W1965876361","doi":"https://doi.org/10.1109/icsm.2012.6405328","mag":"1965876361"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsm.2012.6405328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5008760456","display_name":"David Binkley","orcid":"https://orcid.org/0000-0003-0059-4024"},"institutions":[{"id":"https://openalex.org/I165556055","display_name":"Loyola University Maryland","ror":"https://ror.org/01by1wp65","country_code":"US","type":"education","lineage":["https://openalex.org/I165556055"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dave Binkley","raw_affiliation_strings":["Computer Science Department, Loyola University Maryland, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Loyola University Maryland, Baltimore, USA","institution_ids":["https://openalex.org/I165556055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037074105","display_name":"Dawn Lawrie","orcid":"https://orcid.org/0000-0001-7347-7086"},"institutions":[{"id":"https://openalex.org/I165556055","display_name":"Loyola University Maryland","ror":"https://ror.org/01by1wp65","country_code":"US","type":"education","lineage":["https://openalex.org/I165556055"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawn Lawrie","raw_affiliation_strings":["Computer Science Department, Loyola University Maryland, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Loyola University Maryland, Baltimore, USA","institution_ids":["https://openalex.org/I165556055"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032120182","display_name":"Christopher Uehlinger","orcid":null},"institutions":[{"id":"https://openalex.org/I165556055","display_name":"Loyola University Maryland","ror":"https://ror.org/01by1wp65","country_code":"US","type":"education","lineage":["https://openalex.org/I165556055"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Uehlinger","raw_affiliation_strings":["Computer Science Department, Loyola University Maryland, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Loyola University Maryland, Baltimore, USA","institution_ids":["https://openalex.org/I165556055"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.538,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":12,"citation_normalized_percentile":{"value":0.765071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":86,"max":87},"biblio":{"volume":null,"issue":null,"first_page":"588","last_page":"591"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9999,"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":0.9999,"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":0.9936,"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":0.9932,"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/normalization","display_name":"Normalization","score":0.81053007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86766165},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.81053007},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7793299},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.65559703},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.650872},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.57091033},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.56256473},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.56136227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5494407},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.53926355},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46446413},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36245096},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11167818},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsm.2012.6405328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.74,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":15,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1539495021","https://openalex.org/W1972420078","https://openalex.org/W1984132113","https://openalex.org/W1990190154","https://openalex.org/W2012313588","https://openalex.org/W2027460109","https://openalex.org/W2110220994","https://openalex.org/W2121775589","https://openalex.org/W2128581098","https://openalex.org/W2128737833","https://openalex.org/W2147296306","https://openalex.org/W2154027310","https://openalex.org/W2171238733","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W4392500255","https://openalex.org/W4378651134","https://openalex.org/W4252684102","https://openalex.org/W4240253816","https://openalex.org/W3120493416","https://openalex.org/W3096456556","https://openalex.org/W3029691491","https://openalex.org/W2591697403","https://openalex.org/W2352307597","https://openalex.org/W2098192829"],"abstract_inverted_index":{"Tool":[0],"support":[1],"is":[2,138,164,176],"crucial":[3],"to":[4,140],"modern":[5],"software":[6,56,80],"development,":[7],"evolution,":[8],"and":[9,28,58,82,101,146,149],"maintenance.":[10],"Early":[11],"tools":[12,27,31,95],"reused":[13],"the":[14,19,40,48,63,85,108,126,129,142,171],"static":[15],"analysis":[16,26],"performed":[17],"by":[18,24],"compiler.":[20],"These":[21],"were":[22],"followed":[23],"dynamic":[25],"more":[29],"recently":[30],"that":[32,42,76],"exploit":[33],"natural":[34,64,113],"language.":[35],"This":[36,89],"later":[37],"class":[38],"has":[39],"advantage":[41],"it":[43,137],"can":[44],"incorporate":[45],"not":[46],"only":[47],"code,":[49],"but":[50],"artifacts":[51,81],"from":[52,75,97],"all":[53],"phases":[54],"of":[55,110,128,144],"construction":[57],"its":[59],"subsequent":[60],"evolution.":[61],"Unfortunately,":[62],"language":[65,114],"found":[66],"in":[67,78],"source":[68,130],"code":[69],"often":[70],"uses":[71],"a":[72,111,154],"vocabulary":[73,86,127],"different":[74],"used":[77],"other":[79,134],"thus":[83],"increases":[84],"mismatch":[87],"problem.":[88],"problem":[90],"exists":[91],"because":[92],"many":[93],"natural-language":[94],"imported":[96],"Information":[98],"Retrieval":[99],"(IR)":[100],"Natural":[102],"Language":[103],"Processing":[104],"(NLP)":[105],"implicitly":[106],"assume":[107],"use":[109],"single":[112],"vocabulary.":[115],"Vocabulary":[116],"normalization,":[117],"which":[118],"goes":[119],"well":[120],"beyond":[121],"simple":[122],"identifier":[123],"splitting,":[124],"brings":[125],"into":[131],"line":[132],"with":[133,159],"artifacts.":[135],"Consequently,":[136],"expected":[139],"improve":[141],"performance":[143],"existing":[145],"future":[147],"IR":[148],"NLP":[150],"based":[151],"tools.":[152],"As":[153],"case":[155],"study,":[156],"an":[157,160],"experiment":[158],"LSI-based":[161],"feature":[162],"locator":[163],"replicated.":[165],"Normalization":[166],"universally":[167],"improves":[168],"performance.":[169],"For":[170],"tersest":[172],"queries,":[173],"this":[174],"improvement":[175],"over":[177],"180%":[178],"(p":[179],"<;":[180],"0.0001).":[181]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1965876361","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2024-12-10T11:54:43.014818","created_date":"2016-06-24"}