{"id":"https://openalex.org/W3039617656","doi":"https://doi.org/10.1007/s11219-020-09520-3","title":"Predicting technical debt from commit contents: reproduction and extension with automated feature selection","display_name":"Predicting technical debt from commit contents: reproduction and extension with automated feature selection","publication_year":2020,"publication_date":"2020-07-04","ids":{"openalex":"https://openalex.org/W3039617656","doi":"https://doi.org/10.1007/s11219-020-09520-3","mag":"3039617656"},"language":"en","primary_location":{"id":"doi:10.1007/s11219-020-09520-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11219-020-09520-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11219-020-09520-3.pdf","source":{"id":"https://openalex.org/S7504070","display_name":"Software Quality Journal","issn_l":"0963-9314","issn":["0963-9314","1573-1367"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Quality Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11219-020-09520-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048541729","display_name":"Leevi Rantala","orcid":"https://orcid.org/0000-0003-0258-8904"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Leevi Rantala","raw_affiliation_strings":["M3S / ITEE / University of Oulu, P.O.B. 4500, 90014 University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"M3S / ITEE / University of Oulu, P.O.B. 4500, 90014 University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078824435","display_name":"Mika M\u00e4ntyl\u00e4","orcid":"https://orcid.org/0000-0002-2841-5879"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mika M\u00e4ntyl\u00e4","raw_affiliation_strings":["M3S / ITEE / University of Oulu, P.O.B. 4500, 90014 University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"M3S / ITEE / University of Oulu, P.O.B. 4500, 90014 University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048541729"],"corresponding_institution_ids":["https://openalex.org/I98381234"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.2255,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90650036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":"4","first_page":"1551","last_page":"1579"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9855999946594238,"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"}},{"id":"https://openalex.org/T11675","display_name":"Open Source Software Innovations","score":0.9609000086784363,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/commit","display_name":"Commit","score":0.7674155235290527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727641224861145},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6216970086097717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5761542320251465},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5609449148178101},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5587561130523682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.55315762758255},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5412461757659912},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5140994191169739},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4926460385322571},{"id":"https://openalex.org/keywords/technical-debt","display_name":"Technical debt","score":0.4917767345905304},{"id":"https://openalex.org/keywords/undo","display_name":"Undo","score":0.48271986842155457},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4498153030872345},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4126219153404236},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.22878098487854004},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20159101486206055},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1762905716896057},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.12297281622886658},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.09406086802482605},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08631601929664612}],"concepts":[{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.7674155235290527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727641224861145},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6216970086097717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5761542320251465},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5609449148178101},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5587561130523682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.55315762758255},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5412461757659912},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5140994191169739},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4926460385322571},{"id":"https://openalex.org/C159198006","wikidata":"https://www.wikidata.org/wiki/Q1532172","display_name":"Technical debt","level":4,"score":0.4917767345905304},{"id":"https://openalex.org/C2780154230","wikidata":"https://www.wikidata.org/wiki/Q513420","display_name":"Undo","level":2,"score":0.48271986842155457},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4498153030872345},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4126219153404236},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.22878098487854004},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20159101486206055},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1762905716896057},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.12297281622886658},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.09406086802482605},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08631601929664612},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11219-020-09520-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11219-020-09520-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11219-020-09520-3.pdf","source":{"id":"https://openalex.org/S7504070","display_name":"Software Quality Journal","issn_l":"0963-9314","issn":["0963-9314","1573-1367"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Quality Journal","raw_type":"journal-article"},{"id":"pmh:oai:oulu.fi:nbnfi-fe2020080347902","is_oa":true,"landing_page_url":"http://urn.fi/urn:nbn:fi-fe2020080347902","pdf_url":null,"source":{"id":"https://openalex.org/S4306400284","display_name":"University of Oulu Repository (University of Oulu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98381234","host_organization_name":"University of Oulu","host_organization_lineage":["https://openalex.org/I98381234"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s11219-020-09520-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11219-020-09520-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11219-020-09520-3.pdf","source":{"id":"https://openalex.org/S7504070","display_name":"Software Quality Journal","issn_l":"0963-9314","issn":["0963-9314","1573-1367"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Quality Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4099999964237213,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1087598865","display_name":null,"funder_award_id":"298020","funder_id":"https://openalex.org/F4320336704","funder_display_name":"Infotech Oulu"},{"id":"https://openalex.org/G159206728","display_name":null,"funder_award_id":"-","funder_id":"https://openalex.org/F4320336704","funder_display_name":"Infotech Oulu"},{"id":"https://openalex.org/G733052","display_name":null,"funder_award_id":"328058","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G7786573680","display_name":null,"funder_award_id":"298020","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320323692","display_name":"Oulun Yliopisto","ror":"https://ror.org/03yj89h83"},{"id":"https://openalex.org/F4320336704","display_name":"Infotech Oulu","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3039617656.pdf","grobid_xml":"https://content.openalex.org/works/W3039617656.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W649920412","https://openalex.org/W1529265328","https://openalex.org/W1556110137","https://openalex.org/W1880262756","https://openalex.org/W1972886276","https://openalex.org/W1972978214","https://openalex.org/W1985266020","https://openalex.org/W1993784968","https://openalex.org/W2006617902","https://openalex.org/W2008596407","https://openalex.org/W2028140375","https://openalex.org/W2038043464","https://openalex.org/W2042571564","https://openalex.org/W2043223258","https://openalex.org/W2045336717","https://openalex.org/W2045837563","https://openalex.org/W2047604680","https://openalex.org/W2056894403","https://openalex.org/W2065565905","https://openalex.org/W2085113749","https://openalex.org/W2097360283","https://openalex.org/W2105776892","https://openalex.org/W2107277166","https://openalex.org/W2108025693","https://openalex.org/W2120194796","https://openalex.org/W2123442489","https://openalex.org/W2126793110","https://openalex.org/W2130602377","https://openalex.org/W2143017621","https://openalex.org/W2151666086","https://openalex.org/W2158139315","https://openalex.org/W2162317738","https://openalex.org/W2166183437","https://openalex.org/W2171319841","https://openalex.org/W2238728730","https://openalex.org/W2250539671","https://openalex.org/W2251771443","https://openalex.org/W2328176404","https://openalex.org/W2341587966","https://openalex.org/W2387719207","https://openalex.org/W2395122565","https://openalex.org/W2395955025","https://openalex.org/W2406986017","https://openalex.org/W2408181256","https://openalex.org/W2461407631","https://openalex.org/W2560823834","https://openalex.org/W2573984204","https://openalex.org/W2577308045","https://openalex.org/W2579161546","https://openalex.org/W2612705982","https://openalex.org/W2740329368","https://openalex.org/W2767729231","https://openalex.org/W2799610300","https://openalex.org/W2803437449","https://openalex.org/W2882319491","https://openalex.org/W2883571047","https://openalex.org/W2884229567","https://openalex.org/W2887004133","https://openalex.org/W2888241476","https://openalex.org/W2921621939","https://openalex.org/W2953320089","https://openalex.org/W2954560898","https://openalex.org/W2963691276","https://openalex.org/W2964244292","https://openalex.org/W2994330170","https://openalex.org/W2999930818","https://openalex.org/W3104077627","https://openalex.org/W3122498858","https://openalex.org/W4294541781","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2115968517","https://openalex.org/W79743612","https://openalex.org/W2575202322","https://openalex.org/W2158967736","https://openalex.org/W1038420441","https://openalex.org/W2114343912","https://openalex.org/W2170927537","https://openalex.org/W2081448291","https://openalex.org/W2395284788","https://openalex.org/W3164808405"],"abstract_inverted_index":{"Abstract":[0],"Self-admitted":[1],"technical":[2,37,83],"debt":[3,84],"refers":[4],"to":[5,67,164,207,212],"sub-optimal":[6],"development":[7],"solutions":[8],"that":[9,34,80,194],"are":[10,149],"expressed":[11],"in":[12,214],"written":[13],"code":[14,86],"comments":[15],"or":[16],"commits.":[17],"We":[18,39,53],"reproduce":[19],"and":[20,49,115,173,205,211],"improve":[21],"on":[22,31],"a":[23,106,175,183,188],"prior":[24,78,107],"work":[25,79,143],"by":[26],"Yan":[27],"et":[28],"al.":[29],"(2018)":[30],"detecting":[32],"commits":[33,88],"introduce":[35],"self-admitted":[36,82],"debt.":[38],"use":[40],"multiple":[41,171],"natural":[42],"language":[43],"processing":[44],"methods:":[45],"Bag-of-Words,":[46],"topic":[47],"modeling,":[48],"word":[50],"embedding":[51],"vectors.":[52],"study":[54],"5":[55],"open-source":[56],"projects.":[57],"Our":[58,93,142],"NLP":[59,152],"approach":[60,94],"uses":[61],"logistic":[62],"Lasso":[63],"regression":[64],"from":[65,77,85],"Glmnet":[66],"automatically":[68,127],"select":[69],"best":[70],"predictor":[71,167,192],"words.":[72,129],"A":[73],"manually":[74,123],"labeled":[75],"dataset":[76],"identified":[81],"level":[87],"serves":[89],"as":[90,199,201],"ground":[91],"truth.":[92],"achieves":[95],"+":[96,116],"0.15":[97],"better":[98,118],"area":[99],"under":[100],"the":[101,133,191,215],"ROC":[102],"curve":[103],"performance":[104],"than":[105],"work,":[108,161],"when":[109,121,169],"comparing":[110,150],"only":[111],"commit":[112],"message":[113],"features,":[114],"0.03":[117],"result":[119],"overall":[120],"replacing":[122],"selected":[124,128],"features":[125],"with":[126,180,197],"In":[130],"both":[131],"cases,":[132],"improvement":[134],"was":[135],"statistically":[136],"significant":[137],"(":[138],"p":[139],"&lt;":[140],"0.0001).":[141],"has":[144],"four":[145],"main":[146],"contributions,":[147],"which":[148],"different":[151],"techniques":[153],"for":[154],"SATD":[155],"detection,":[156],"improved":[157],"results":[158],"over":[159],"previous":[160],"showing":[162],"how":[163],"generate":[165],"generalizable":[166],"words":[168,178,193],"using":[170],"repositories,":[172],"producing":[174],"list":[176,189],"of":[177,190,217],"correlating":[179],"SATD.":[181],"As":[182],"concrete":[184],"result,":[185],"we":[186],"release":[187],"correlate":[195],"positively":[196],"SATD,":[198],"well":[200],"our":[202],"used":[203],"datasets":[204],"scripts":[206],"enable":[208],"replication":[209],"studies":[210],"aid":[213],"creation":[216],"future":[218],"classifiers.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
