{"id":"https://openalex.org/W7223572293","doi":"https://doi.org/10.1007/s10115-026-02898-9","title":"Quality versus quantity: including imperfect training data improves prediction of user satisfaction in software projects","display_name":"Quality versus quantity: including imperfect training data improves prediction of user satisfaction in software projects","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7223572293","doi":"https://doi.org/10.1007/s10115-026-02898-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10115-026-02898-9","doi":"https://doi.org/10.1007/s10115-026-02898-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-026-02898-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-026-02898-9.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-c","anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-d","jufo-2","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10115-026-02898-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068145892","display_name":"\u0141ukasz Radli\u0144ski","orcid":"https://orcid.org/0000-0003-1007-6597","observed_orcids":["https://orcid.org/0000-0003-1007-6597"]},"institutions":[{"id":"https://openalex.org/I155313962","display_name":"West Pomeranian University of Technology in Szczecin","ror":"https://ror.org/0596m7f19","country_code":"PL","type":"education","lineage":["https://openalex.org/I155313962"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"\u0141ukasz Radli\u0144ski","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, West Pomeranian University of Technology in Szczecin, Szczecin, Poland"],"raw_orcid":"https://orcid.org/0000-0003-1007-6597","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, West Pomeranian University of Technology in Szczecin, Szczecin, Poland","institution_ids":["https://openalex.org/I155313962"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5068145892"],"corresponding_institution_ids":["https://openalex.org/I155313962"],"apc_list":{"value":3190,"currency":"USD","value_usd":3190},"apc_paid":{"value":3190,"currency":"USD","value_usd":3190},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86927322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"68","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9423999786376953,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9423999786376953,"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/T10260","display_name":"Software Engineering Research","score":0.04529999941587448,"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/T10470","display_name":"Usability and User Interface Design","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/user-satisfaction-prediction","display_name":"user satisfaction prediction","score":0.9089999794960022},{"id":"https://openalex.org/keywords/software-projects","display_name":"software development projects","score":0.8230000138282776},{"id":"https://openalex.org/keywords/training-data-quality","display_name":"training data quality","score":0.8859999775886536},{"id":"https://openalex.org/keywords/software-quality","display_name":"software quality","score":0.3930000066757202},{"id":"https://openalex.org/keywords/software-metrics","display_name":"software metrics","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293000221252441},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6226999759674072},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C3017893058","wikidata":"https://www.wikidata.org/wiki/Q999278","display_name":"User satisfaction","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4381999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C191511416","wikidata":"https://www.wikidata.org/wiki/Q999278","display_name":"Customer satisfaction","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37380000948905945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C63880386","wikidata":"https://www.wikidata.org/wiki/Q5157592","display_name":"Computer user satisfaction","level":4,"score":0.2777000069618225},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10115-026-02898-9","doi":"https://doi.org/10.1007/s10115-026-02898-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-026-02898-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-026-02898-9.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-c","anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-d","jufo-2","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10115-026-02898-9","doi":"https://doi.org/10.1007/s10115-026-02898-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-026-02898-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-026-02898-9.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-c","anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-d","jufo-2","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223572293.pdf","grobid_xml":"https://content.openalex.org/works/W7223572293.grobid-xml"},"referenced_works_count":94,"referenced_works":["https://openalex.org/W176201993","https://openalex.org/W1570448133","https://openalex.org/W1678356000","https://openalex.org/W1888837269","https://openalex.org/W1970919166","https://openalex.org/W1982160761","https://openalex.org/W1985258161","https://openalex.org/W1994410397","https://openalex.org/W2000642745","https://openalex.org/W2005504865","https://openalex.org/W2005943993","https://openalex.org/W2009786711","https://openalex.org/W2014455254","https://openalex.org/W2033515880","https://openalex.org/W2045260557","https://openalex.org/W2058068298","https://openalex.org/W2058879452","https://openalex.org/W2070567333","https://openalex.org/W2075848956","https://openalex.org/W2090682913","https://openalex.org/W2090954654","https://openalex.org/W2094989614","https://openalex.org/W2097670073","https://openalex.org/W2103018059","https://openalex.org/W2114363693","https://openalex.org/W2117812871","https://openalex.org/W2129707602","https://openalex.org/W2131378644","https://openalex.org/W2133990480","https://openalex.org/W2140180105","https://openalex.org/W2144678826","https://openalex.org/W2153635508","https://openalex.org/W2156614068","https://openalex.org/W2161336914","https://openalex.org/W2162004515","https://openalex.org/W2165698076","https://openalex.org/W2281037394","https://openalex.org/W2282821441","https://openalex.org/W2295598076","https://openalex.org/W2407212869","https://openalex.org/W2474835145","https://openalex.org/W2509487919","https://openalex.org/W2547827133","https://openalex.org/W2610584737","https://openalex.org/W2619070928","https://openalex.org/W2621492583","https://openalex.org/W2735864302","https://openalex.org/W2786715987","https://openalex.org/W2787894218","https://openalex.org/W2788403449","https://openalex.org/W2884443195","https://openalex.org/W2889763677","https://openalex.org/W2896731104","https://openalex.org/W2910010216","https://openalex.org/W2910802015","https://openalex.org/W2911964244","https://openalex.org/W2916969377","https://openalex.org/W2932881901","https://openalex.org/W2945526235","https://openalex.org/W2964159205","https://openalex.org/W2969624920","https://openalex.org/W2978567953","https://openalex.org/W2981731882","https://openalex.org/W3006818076","https://openalex.org/W3036738089","https://openalex.org/W3041133507","https://openalex.org/W3047430083","https://openalex.org/W3089378600","https://openalex.org/W3108417339","https://openalex.org/W3116361147","https://openalex.org/W3121086480","https://openalex.org/W3127971289","https://openalex.org/W3129952141","https://openalex.org/W3141941927","https://openalex.org/W3168227435","https://openalex.org/W3170657538","https://openalex.org/W3174740339","https://openalex.org/W3195238303","https://openalex.org/W4226169266","https://openalex.org/W4226239514","https://openalex.org/W4250288019","https://openalex.org/W4252198446","https://openalex.org/W4252684946","https://openalex.org/W4292387237","https://openalex.org/W4294541781","https://openalex.org/W4324374545","https://openalex.org/W4362475637","https://openalex.org/W4385755296","https://openalex.org/W4388539339","https://openalex.org/W4389256065","https://openalex.org/W4405394684","https://openalex.org/W4405845734","https://openalex.org/W4414567732","https://openalex.org/W4416381670"],"related_works":["https://openalex.org/W3141941927","https://openalex.org/W2403875291","https://openalex.org/W2030724731","https://openalex.org/W6959690351","https://openalex.org/W7053389140","https://openalex.org/W3175194807","https://openalex.org/W3175594738","https://openalex.org/W7098763723","https://openalex.org/W2913546123","https://openalex.org/W2775425720"],"abstract_inverted_index":{"This":[0,21],"study":[1,22],"explored":[2],"the":[3,18,24,32,42,52,55,59,108,120,135,148,166,172],"impact":[4],"of":[5,26,54,122,145,160,174,191,217],"data":[6,33,40,110,123,141,149,213,218],"quality":[7],"and":[8,57,79,129,154,186,221],"quantity":[9],"on":[10,91,102,197],"predicting":[11,87],"user":[12,88,192],"satisfaction":[13,89,193],"in":[14,41],"software":[15],"projects":[16],"using":[17],"ISBSG":[19,181],"dataset.":[20],"evaluated":[23],"performance":[25],"machine":[27],"learning":[28],"models":[29,86,196],"by":[30],"varying":[31],"variants,":[34,219],"i.e.":[35],"strategies":[36],"for":[37],"including":[38],"low-quality":[39,96,206],"training":[43,109],"subsets.":[44],"A":[45,143],"rigorous":[46],"methodology":[47],"was":[48,165],"employed":[49],"to":[50],"ensure":[51],"reliability":[53],"results":[56],"validate":[58],"conclusions.":[60],"It":[61],"involved":[62],"repeated":[63],"nested":[64],"cross-validation,":[65],"standardised":[66],"accuracy,":[67,114],"win\u2013tie\u2013loss":[68],"analysis,":[69],"matched-pairs":[70],"rank":[71],"biserial":[72],"correlation,":[73],"Scott\u2013Knott":[74],"effect":[75],"size":[76],"difference":[77],"test,":[78],"Kendall\u2019s":[80],"W.":[81],"The":[82],"findings":[83,170],"suggest":[84],"that":[85],"trained":[90,101],"larger":[92],"datasets,":[93,184,200],"despite":[94],"containing":[95],"data,":[97,207],"usually":[98],"outperformed":[99],"those":[100],"smaller,":[103],"high-quality":[104],"datasets.":[105],"Hence,":[106],"expanding":[107],"can":[111],"improve":[112],"predictive":[113,189],"even":[115,201],"if":[116,202],"it":[117],"comes":[118],"at":[119,157],"cost":[121],"quality.":[124],"Support":[125],"vector":[126],"machines":[127],"(SVM)":[128],"extreme":[130],"gradient":[131],"boosting":[132],"trees":[133],"delivered":[134],"most":[136,167],"accurate":[137],"predictions":[138],"across":[139],"all":[140,152],"variants.":[142],"combination":[144],"SVM":[146],"with":[147,180,211],"variant":[150],"involving":[151],"cases":[153],"attributes,":[155],"where":[156],"least":[158],"40%":[159],"values":[161],"were":[162],"valid":[163],"(non-missing),":[164],"accurate.":[168],"Obtained":[169],"enabled":[171],"formulation":[173],"a":[175],"preliminary":[176],"recommendation:":[177],"when":[178,209],"working":[179],"or":[182],"similar":[183],"researchers":[185],"practitioners":[187],"prioritising":[188],"accuracy":[190],"should":[194],"train":[195],"relatively":[198],"large":[199],"they":[203],"contain":[204],"some":[205],"especially":[208],"dealing":[210],"limited":[212],"availability.":[214],"Provided":[215],"rankings":[216],"models,":[220],"combinations":[222],"may":[223],"help":[224],"set":[225],"up":[226],"future":[227],"studies.":[228]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-26T00:00:00"}