{"id":"https://openalex.org/W3094872753","doi":"https://doi.org/10.1145/3416505.3423562","title":"Speeding up the data extraction of machine learning approaches: a distributed framework","display_name":"Speeding up the data extraction of machine learning approaches: a distributed framework","publication_year":2020,"publication_date":"2020-11-06","ids":{"openalex":"https://openalex.org/W3094872753","doi":"https://doi.org/10.1145/3416505.3423562","mag":"3094872753"},"language":"en","primary_location":{"id":"doi:10.1145/3416505.3423562","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3416505.3423562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGSOFT International Workshop on Machine-Learning Techniques for Software-Quality Evaluation","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/A5078777091","display_name":"Martin Steinhauer","orcid":null},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Martin Steinhauer","raw_affiliation_strings":["University of Salerno, Italy"],"affiliations":[{"raw_affiliation_string":"University of Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033738898","display_name":"Fabio Palomba","orcid":"https://orcid.org/0000-0001-9337-5116"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Palomba","raw_affiliation_strings":["University of Salerno, Italy"],"affiliations":[{"raw_affiliation_string":"University of Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078777091"],"corresponding_institution_ids":["https://openalex.org/I131729948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15880071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9958999752998352,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8416903614997864},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.763572633266449},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6480329632759094},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6039402484893799},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5399399399757385},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.48080745339393616},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4293064773082733},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42686212062835693},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42187416553497314},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4124700725078583},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40928468108177185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3086501657962799},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.140804260969162},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09154626727104187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416903614997864},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.763572633266449},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6480329632759094},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6039402484893799},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5399399399757385},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.48080745339393616},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4293064773082733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42686212062835693},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42187416553497314},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4124700725078583},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40928468108177185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3086501657962799},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.140804260969162},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09154626727104187},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3416505.3423562","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3416505.3423562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGSOFT International Workshop on Machine-Learning Techniques for Software-Quality Evaluation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W776871969","https://openalex.org/W1972386298","https://openalex.org/W2034158106","https://openalex.org/W2087946700","https://openalex.org/W2119738171","https://openalex.org/W2122414758","https://openalex.org/W2173213060","https://openalex.org/W2795027827","https://openalex.org/W2899407111","https://openalex.org/W2945478369","https://openalex.org/W2955366688","https://openalex.org/W3099060507","https://openalex.org/W3106502818","https://openalex.org/W3140103367","https://openalex.org/W4300007223"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"In":[0],"the":[1,12,73,88],"last":[2],"decade,":[3],"mining":[4,85,100],"software":[5,101],"repositories":[6,102],"(MSR)":[7],"has":[8],"become":[9],"one":[10],"of":[11,33,46,72,78],"most":[13],"important":[14],"sources":[15],"to":[16,49,103,111,117],"feed":[17,104],"machine":[18,105],"learning":[19,106],"models.":[20],"Especially":[21],"open-source":[22],"projects":[23],"on":[24],"platforms":[25],"like":[26],"GitHub":[27],"are":[28,108],"providing":[29],"a":[30,44,94],"tremendous":[31],"amount":[32],"data":[34,51,74],"and":[35,55,62,121],"make":[36],"them":[37,79],"easily":[38],"accessible.":[39],"Nevertheless,":[40],"there":[41],"is":[42],"still":[43],"lack":[45],"standardized":[47],"pipelines":[48],"extract":[50],"in":[52,98],"an":[53,83],"automated":[54,84],"fast":[56],"way.":[57],"Even":[58],"though":[59],"several":[60],"frameworks":[61],"tools":[63],"exist":[64],"which":[65],"can":[66],"fulfill":[67],"specific":[68],"tasks":[69,115],"or":[70],"parts":[71],"extraction":[75],"process,":[76],"none":[77],"allow":[80],"neither":[81],"building":[82],"pipeline":[86],"nor":[87],"possibility":[89],"for":[90],"full":[91],"parallelization.":[92],"As":[93],"consequence,":[95],"researchers":[96],"interested":[97],"using":[99],"models":[107],"often":[109],"forced":[110],"re-implement":[112],"commonly":[113],"used":[114],"leading":[116],"additional":[118],"development":[119],"time":[120],"libraries":[122],"may":[123],"not":[124],"be":[125],"integrated":[126],"optimally.":[127]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}