{"id":"https://openalex.org/W4300581206","doi":"https://doi.org/10.1145/3196398.3196444","title":"Natural language or not (NLON)","display_name":"Natural language or not (NLON)","publication_year":2018,"publication_date":"2018-05-28","ids":{"openalex":"https://openalex.org/W4300581206","doi":"https://doi.org/10.1145/3196398.3196444"},"language":"en","primary_location":{"id":"doi:10.1145/3196398.3196444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3196398.3196444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.07292","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Mika V. M\u00e4ntyl\u00e4","raw_affiliation_strings":["University of Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017685793","display_name":"Fabio Calefato","orcid":"https://orcid.org/0000-0003-2654-1588"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Calefato","raw_affiliation_strings":["University of Bari, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bari, Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067646491","display_name":"Ma\u00eblick Claes","orcid":"https://orcid.org/0000-0003-2259-3946"},"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":"Maelick Claes","raw_affiliation_strings":["University of Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078824435"],"corresponding_institution_ids":["https://openalex.org/I98381234"],"apc_list":null,"apc_paid":null,"fwci":1.78597009,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89376212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"387","last_page":"391"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8230677247047424},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6622723340988159},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6367312669754028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5849934816360474},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5603978633880615},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5156561136245728},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5095198750495911},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4881587624549866},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4277638792991638},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4194159507751465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3500567674636841},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34000587463378906},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.209130197763443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230677247047424},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6622723340988159},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6367312669754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849934816360474},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5603978633880615},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5156561136245728},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5095198750495911},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4881587624549866},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4277638792991638},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4194159507751465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3500567674636841},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34000587463378906},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.209130197763443},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3196398.3196444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3196398.3196444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.07292","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.07292","pdf_url":"https://arxiv.org/pdf/1803.07292","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.07292","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.07292","pdf_url":"https://arxiv.org/pdf/1803.07292","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[{"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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1916584426","https://openalex.org/W1944317963","https://openalex.org/W2025599150","https://openalex.org/W2074218040","https://openalex.org/W2096451472","https://openalex.org/W2118978333","https://openalex.org/W2121972257","https://openalex.org/W2153031028","https://openalex.org/W2154290668","https://openalex.org/W2356036115","https://openalex.org/W2559490865","https://openalex.org/W2571253853","https://openalex.org/W2571312737","https://openalex.org/W2604873636","https://openalex.org/W2727177317","https://openalex.org/W3102444842"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W2741781807"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,40],"natural":[3,27,58],"language":[4,28,59,70],"processing":[5],"(NLP)":[6],"is":[7,57,113,137],"gaining":[8],"popularity":[9],"in":[10,43,146],"software":[11,44,147],"engineering.":[12,45],"In":[13],"order":[14],"to":[15,25,78,125,144],"correctly":[16],"perform":[17],"NLP,":[18],"we":[19,75],"must":[20],"pre-process":[21],"the":[22,41,83],"textual":[23,55],"information":[24],"separate":[26],"from":[29,97,123],"other":[30],"information,":[31],"such":[32],"as":[33,99,159],"log":[34],"messages,":[35],"that":[36],"are":[37,76,157],"often":[38],"part":[39],"communication":[42],"We":[46],"present":[47],"a":[48],"simple":[49],"approach":[50,132],"for":[51,106,162],"classifying":[52],"whether":[53],"some":[54],"input":[56],"or":[60],"not.":[61],"Although":[62],"our":[63,100,131],"NLoN":[64],"package":[65],"relies":[66],"on":[67,89],"only":[68],"11":[69],"features":[71],"and":[72,102,115,155],"character":[73],"tri-grams,":[74],"able":[77],"achieve":[79],"an":[80,160],"area":[81],"under":[82],"ROC":[84,121],"curve":[85],"performances":[86,122],"between":[87],"0.976-0.987":[88],"three":[90],"different":[91],"data":[92,156],"sources,":[93],"with":[94,119,128],"Lasso":[95],"regression":[96],"Glmnet":[98],"learner":[101],"two":[103],"human":[104],"raters":[105],"providing":[107],"ground":[108],"truth.":[109],"Cross-source":[110],"prediction":[111],"performance":[112,135],"lower":[114],"has":[116],"more":[117,139],"fluctuation":[118],"top":[120],"0.913":[124],"0.980.":[126],"Compared":[127],"prior":[129],"work,":[130],"offers":[133],"similar":[134],"but":[136],"considerably":[138],"lightweight,":[140],"making":[141],"it":[142],"easier":[143],"apply":[145],"engineering":[148],"text":[149],"mining":[150],"pipelines.":[151],"Our":[152],"source":[153],"code":[154],"provided":[158],"R-package":[161],"further":[163],"improvements.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2022-10-03T00:00:00"}
