{"id":"https://openalex.org/W2517352662","doi":"https://doi.org/10.1145/2972958.2972963","title":"Measuring the Stylistic Inconsistency in Software Projects using Hierarchical Agglomerative Clustering","display_name":"Measuring the Stylistic Inconsistency in Software Projects using Hierarchical Agglomerative Clustering","publication_year":2016,"publication_date":"2016-08-26","ids":{"openalex":"https://openalex.org/W2517352662","doi":"https://doi.org/10.1145/2972958.2972963","mag":"2517352662"},"language":"en","primary_location":{"id":"doi:10.1145/2972958.2972963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2972958.2972963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the The 12th International Conference on Predictive Models and Data Analytics in Software Engineering","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/A5010586673","display_name":"Qing Mi","orcid":"https://orcid.org/0000-0001-5063-3189","observed_orcids":["https://orcid.org/0000-0001-5063-3189"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Mi","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051403641","display_name":"Jacky Keung","orcid":"https://orcid.org/0000-0002-3803-9600","observed_orcids":["https://orcid.org/0000-0002-3803-9600"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jacky Keung","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024627947","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0003-1641-135X","observed_orcids":["https://orcid.org/0000-0003-1641-135X","https://orcid.org/0000-0002-9106-491X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["Search Engine Department, Beijing Sogou Technology Development Co., Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Search Engine Department, Beijing Sogou Technology Development Co., Ltd, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5167,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.61883794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9900000095367432,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.8073853254318237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6310182809829712},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5416953563690186},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4622578024864197},{"id":"https://openalex.org/keywords/hierarchical-clustering-of-networks","display_name":"Hierarchical clustering of networks","score":0.45820996165275574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.404043972492218},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35668057203292847},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34975266456604004},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.1891683042049408},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15654665231704712},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.06876301765441895}],"concepts":[{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.8073853254318237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6310182809829712},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5416953563690186},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4622578024864197},{"id":"https://openalex.org/C82261393","wikidata":"https://www.wikidata.org/wiki/Q17038699","display_name":"Hierarchical clustering of networks","level":5,"score":0.45820996165275574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.404043972492218},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35668057203292847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34975266456604004},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.1891683042049408},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15654665231704712},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.06876301765441895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2972958.2972963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2972958.2972963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the The 12th International Conference on Predictive Models and Data Analytics in Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5400000214576721}],"x_sdgs":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W101836494","https://openalex.org/W956207200","https://openalex.org/W1575235053","https://openalex.org/W1969685458","https://openalex.org/W1973423365","https://openalex.org/W1999335744","https://openalex.org/W2001463647","https://openalex.org/W2005247769","https://openalex.org/W2010452235","https://openalex.org/W2016381774","https://openalex.org/W2019284588","https://openalex.org/W2035781078","https://openalex.org/W2038546291","https://openalex.org/W2039603939","https://openalex.org/W2044555705","https://openalex.org/W2072164438","https://openalex.org/W2099629936","https://openalex.org/W2115998851","https://openalex.org/W2140609933","https://openalex.org/W2345181087","https://openalex.org/W2414895359","https://openalex.org/W2537467158"],"related_works":["https://openalex.org/W2592952084","https://openalex.org/W4281642079","https://openalex.org/W3152647962","https://openalex.org/W4312222690","https://openalex.org/W2167118705","https://openalex.org/W2153474479","https://openalex.org/W3099482891","https://openalex.org/W2091561509","https://openalex.org/W2394938095","https://openalex.org/W1989337993"],"abstract_inverted_index":{"Background:":[0],"Although":[1],"many":[2],"software":[3,54,99,233],"engineering":[4],"methodologies":[5],"and":[6,64,71,160,202,226],"guidelines":[7],"are":[8,32,109],"provided,":[9],"it":[10],"is":[11,50,62,176,191],"common":[12],"that":[13,65],"developers":[14],"apply":[15],"their":[16],"very":[17],"own":[18],"programming":[19,30,95,122,139,185,207],"styles":[20,31],"to":[21,119,133],"the":[22,45,53,60,86,91,127,136,158,167,181,229],"source":[23,146,188],"code":[24],"being":[25],"produced.":[26],"These":[27],"individually":[28],"preferred":[29],"more":[33],"comprehensive":[34],"for":[35,85,193,205,216,232],"themselves,":[36],"but":[37],"may":[38],"well":[39],"conflict":[40],"with":[41,174,218],"each":[42],"other.":[43],"Thus,":[44],"problem":[46],"of":[47,88,94,114,138,162,178,184],"stylistic":[48,106],"inconsistency":[49,92,182],"inevitable":[51],"during":[52],"development":[55],"process":[56],"involving":[57],"multiple":[58],"developers,":[59],"result":[61],"undesirable":[63],"will":[66],"significantly":[67],"degrade":[68],"program":[69,224],"readability":[70,225],"maintainability.":[72],"Aims:":[73],"Given":[74],"limited":[75],"understanding":[76],"in":[77,116],"this":[78],"regard,":[79],"we":[80,125],"perform":[81],"an":[82,117,200],"empirical":[83,155],"analysis":[84],"purpose":[87],"quantitatively":[89,134],"measuring":[90,135],"degree":[93,183],"style":[96,140,186,208],"within":[97],"a":[98,112,212,220],"project":[100],"team.":[101],"Method:":[102],"We":[103],"first":[104],"propose":[105],"fingerprints,":[107],"which":[108,190],"represented":[110],"as":[111],"set":[113],"attribute-counting-metrics,":[115],"attempt":[118],"characterize":[120],"different":[121,150],"styles.":[123],"Then":[124],"adopt":[126],"hierarchical":[128],"agglomerative":[129],"clustering":[130,169],"(HAC)":[131],"technique":[132],"proximity":[137],"based":[141],"on":[142],"six":[143],"C/C++":[144],"open":[145],"projects":[147],"chosen":[148],"from":[149],"application":[151],"domains.":[152],"Results:":[153],"The":[154],"results":[156],"demonstrate":[157],"feasibility":[159],"validity":[161],"our":[163],"fingerprinting":[164],"methodology.":[165],"Moreover,":[166],"proposed":[168,199],"procedure":[170],"utilizing":[171],"HAC":[172],"algorithm":[173],"dendrograms":[175],"capable":[177],"effectively":[179],"illustrating":[180],"among":[187],"files,":[189],"significant":[192],"future":[194],"research.":[195],"Conclusions:":[196],"This":[197],"study":[198],"effective":[201],"efficient":[203],"approach":[204],"analyzing":[206],"inconsistency,":[209],"supported":[210],"by":[211],"sound":[213],"theoretical":[214],"basis":[215],"dealing":[217],"such":[219],"problem.":[221],"Ultimately":[222],"improving":[223],"therefore":[227],"reduce":[228],"maintenance":[230],"overhead":[231],"projects.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2025-10-10T00:00:00"}