{"id":"https://openalex.org/W3204784274","doi":"https://doi.org/10.1145/3474624.3477067","title":"Hierarchical Cluster Labeling of Software Requirements using Contextual Word Embeddings","display_name":"Hierarchical Cluster Labeling of Software Requirements using Contextual Word Embeddings","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3204784274","doi":"https://doi.org/10.1145/3474624.3477067","mag":"3204784274"},"language":"en","primary_location":{"id":"doi:10.1145/3474624.3477067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474624.3477067","pdf_url":null,"source":{"id":"https://openalex.org/S4306417862","display_name":"Brazilian Symposium on Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Brazilian Symposium on Software Engineering","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/A5054595587","display_name":"Adailton Ferreira De Ara\u00fajo","orcid":"https://orcid.org/0000-0002-2392-4818"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Adailton Araujo","raw_affiliation_strings":["University of S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103168466","display_name":"Ricardo Marcondes Marcacini","orcid":"https://orcid.org/0000-0002-2309-3487"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ricardo Marcacini","raw_affiliation_strings":["University of S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054595587"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":0.8509,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71072978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"297","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9962999820709229,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7859444618225098},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6557145714759827},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5767089128494263},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5150392055511475},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3877136707305908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3498342037200928},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13959839940071106},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0984896719455719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859444618225098},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6557145714759827},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5767089128494263},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5150392055511475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3877136707305908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3498342037200928},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13959839940071106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0984896719455719},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474624.3477067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474624.3477067","pdf_url":null,"source":{"id":"https://openalex.org/S4306417862","display_name":"Brazilian Symposium on Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Brazilian Symposium on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2116411636","display_name":null,"funder_award_id":"426663/2018-7","funder_id":"https://openalex.org/F4320335042","funder_display_name":"National Council for Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320335042","display_name":"National Council for Scientific Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2112143630","https://openalex.org/W2153579005","https://openalex.org/W2203955288","https://openalex.org/W2268999904","https://openalex.org/W2493916176","https://openalex.org/W2522291077","https://openalex.org/W2598457223","https://openalex.org/W2621107543","https://openalex.org/W2761329858","https://openalex.org/W2892181857","https://openalex.org/W2920187809","https://openalex.org/W2976051099","https://openalex.org/W2979641802","https://openalex.org/W2994579778","https://openalex.org/W3119792886","https://openalex.org/W3157844032"],"related_works":["https://openalex.org/W1569283511","https://openalex.org/W4236193183","https://openalex.org/W2053866214","https://openalex.org/W2607505004","https://openalex.org/W2231795205","https://openalex.org/W2107962325","https://openalex.org/W2523632547","https://openalex.org/W2143882141","https://openalex.org/W3204019825","https://openalex.org/W2296205523"],"abstract_inverted_index":{"The":[0],"popularization":[1],"of":[2,41,44,140,193],"social":[3],"media":[4],"has":[5],"motivated":[6],"research":[7,219],"into":[8,160],"machine":[9],"learning":[10],"methods":[11,22,56,92],"for":[12,115,221],"software":[13,24,33,45,105,116,142,158,176,195],"requirements":[14,64,90,117,159,177,223],"extraction":[15,91],"from":[16,48,67,203],"user":[17],"comments":[18],"and":[19,39,81,87,137,162,182,189,214,218],"reviews.":[20],"These":[21],"analyze":[23],"review":[25,201],"datasets":[26,202],"to":[27,123,132,165,178],"classify":[28],"some":[29],"textual":[30],"excerpts":[31],"as":[32],"requirements,":[34,143],"which":[35,145],"allows":[36],"the":[37,42,49,54,72,141,146,157,169,194],"management":[38],"monitoring":[40],"evolution":[43],"quality":[46],"directly":[47],"crowd":[50],"users\u2019":[51],"perspective.":[52],"However,":[53],"existing":[55],"have":[57],"two":[58],"major":[59],"limitations.":[60],"First,":[61],"several":[62],"duplicate":[63,188],"are":[65,148],"extracted":[66],"reviews":[68],"because":[69],"users":[70],"write":[71],"same":[73],"requirement":[74,166],"in":[75,144,168],"different":[76,97,190],"ways":[77],"by":[78,150],"using":[79,200],"synonyms":[80],"non-technical":[82],"language,":[83],"often":[84],"with":[85,96,186],"misspellings":[86],"ambiguity.":[88],"Second,":[89],"do":[93],"not":[94],"deal":[95],"granularity":[98,191],"levels,":[99],"thereby":[100,184],"ignoring":[101],"hierarchical":[102,111],"relationships":[103],"between":[104],"requirements.":[106,196],"This":[107],"paper":[108],"presents":[109,215],"a":[110,134],"cluster":[112,181],"labeling":[113],"approach":[114,155,210],"based":[118],"on":[119],"contextual":[120,151],"word":[121,152],"embeddings":[122],"address":[124],"these":[125],"challenges.":[126],"We":[127],"explore":[128],"neural":[129],"language":[130],"models":[131],"obtain":[133],"more":[135],"semantic":[136],"robust":[138],"representation":[139],"texts":[147],"represented":[149],"embeddings.":[153],"Our":[154],"organizes":[156],"clusters":[161],"sub-clusters":[163],"according":[164],"similarities":[167],"embedding":[170],"space.":[171],"Finally,":[172],"we":[173],"select":[174],"representative":[175],"label":[179],"each":[180],"sub-cluster,":[183],"dealing":[185],"both":[187],"levels":[192],"An":[197],"experimental":[198],"evaluation":[199],"8":[204],"mobile":[205],"apps":[206],"shows":[207],"that":[208],"our":[209],"obtains":[211],"promising":[212],"results":[213],"new":[216],"ideas":[217],"directions":[220],"data-driven":[222],"engineering.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
