{"id":"https://openalex.org/W3014188249","doi":"https://doi.org/10.1145/3341105.3373992","title":"Data augmentation and semi-supervised learning for deep neural networks-based text classifier","display_name":"Data augmentation and semi-supervised learning for deep neural networks-based text classifier","publication_year":2020,"publication_date":"2020-03-29","ids":{"openalex":"https://openalex.org/W3014188249","doi":"https://doi.org/10.1145/3341105.3373992","mag":"3014188249"},"language":"en","primary_location":{"id":"doi:10.1145/3341105.3373992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341105.3373992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341105.3373992","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3341105.3373992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053168102","display_name":"Heereen Shim","orcid":"https://orcid.org/0000-0003-3761-2310"},"institutions":[{"id":"https://openalex.org/I4210122849","display_name":"Philips (Netherlands)","ror":"https://ror.org/02p2bgp27","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210122849"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Heereen Shim","raw_affiliation_strings":["Philips Research, Eindhoven, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Philips Research, Eindhoven, the Netherlands","institution_ids":["https://openalex.org/I4210122849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018787960","display_name":"Stijn Luca","orcid":"https://orcid.org/0000-0002-6781-7870"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stijn Luca","raw_affiliation_strings":["Ghent University, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079803500","display_name":"Dietwig Lowet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122849","display_name":"Philips (Netherlands)","ror":"https://ror.org/02p2bgp27","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210122849"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dietwig Lowet","raw_affiliation_strings":["Philips Research, Eindhoven, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Philips Research, Eindhoven, the Netherlands","institution_ids":["https://openalex.org/I4210122849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016823997","display_name":"Bart Vanrumste","orcid":"https://orcid.org/0000-0002-9409-935X"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bart Vanrumste","raw_affiliation_strings":["KU Leuven, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1119","last_page":"1126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9943000078201294,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9943000078201294,"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":0.9941999912261963,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.991100013256073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7781357169151306},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.7078803777694702},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6913353800773621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6334906220436096},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6206085681915283},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.603987455368042},{"id":"https://openalex.org/keywords/labelling","display_name":"Labelling","score":0.570767343044281},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5104888677597046},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4512813985347748},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43801671266555786},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4244105815887451},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4112577438354492},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38807323575019836},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32862621545791626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781357169151306},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.7078803777694702},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6913353800773621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6334906220436096},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6206085681915283},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.603987455368042},{"id":"https://openalex.org/C2780523633","wikidata":"https://www.wikidata.org/wiki/Q380709","display_name":"Labelling","level":2,"score":0.570767343044281},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5104888677597046},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4512813985347748},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43801671266555786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4244105815887451},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4112577438354492},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38807323575019836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32862621545791626},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3341105.3373992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341105.3373992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341105.3373992","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/652517","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/652517","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Annual ACM Symposium on Applied Computing, Brno, Czech Republic, 30 March - 3 April 2020","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:archive.ugent.be:8656299","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/8656299","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 35th Annual ACM Symposium on Applied Computing (SAC'20)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3341105.3373992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341105.3373992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341105.3373992","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6102844168","display_name":"HEalth related Activity Recognition system based on IoT \u2013 an interdisciplinary training program for young researchers","funder_award_id":"766139","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3014188249.pdf","grobid_xml":"https://content.openalex.org/works/W3014188249.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2018832388","https://openalex.org/W2163605009","https://openalex.org/W2251658415","https://openalex.org/W2962762898","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2161052216","https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W2786391746","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W2991483587","https://openalex.org/W3163689946","https://openalex.org/W4287890939"],"abstract_inverted_index":{"User":[0],"feedback":[1],"is":[2,42,54,64,83],"essential":[3],"for":[4,166],"understanding":[5],"user":[6],"needs.":[7],"In":[8,151],"this":[9],"paper,":[10],"we":[11,49,158],"use":[12],"free-text":[13],"obtained":[14],"from":[15],"a":[16,23,37,51,55],"survey":[17],"on":[18],"sleep-related":[19],"issues":[20],"to":[21,30,66,69,85],"build":[22],"deep":[24,33],"neural":[25,34],"networks-based":[26],"text":[27],"classifier.":[28],"However,":[29],"train":[31,76],"the":[32,71,74,80,95,98,113,131,135,155,161],"networks":[35],"model,":[36],"lot":[38],"of":[39,57,73,105,122,133,141,163],"labelled":[40,67,164],"data":[41,47,58,62,68,88,99,116,148,165],"needed.":[43],"To":[44],"reduce":[45,160],"manual":[46],"labelling,":[48],"propose":[50],"method":[52,157],"which":[53],"combination":[56,132],"augmentation":[59,63,100,117],"and":[60,78],"pseudo-labelling:":[61],"applied":[65],"increase":[70],"size":[72],"initial":[75],"set":[77],"then":[79],"trained":[81],"model":[82,96,114,136],"used":[84],"annotate":[86],"unlabelled":[87],"with":[89,97,124,130,143,149,154],"pseudo-labels.":[90],"The":[91],"result":[92],"shows":[93],"that":[94],"achieves":[101,118,137],"macro-averaged":[102,119,138],"f1":[103,120,139],"score":[104,121,140],"65.2%":[106],"while":[107,168],"using":[108,145],"4,300":[109],"training":[110,127,147,167],"data,":[111],"whereas":[112],"without":[115],"68.2%":[123],"around":[125],"14,000":[126],"data.":[128],"Furthermore,":[129],"pseudo-labelling,":[134],"62.7%":[142],"only":[144],"1,400":[146],"labels.":[150],"other":[152],"words,":[153],"proposed":[156],"can":[159],"amount":[162],"achieving":[169],"relatively":[170],"good":[171],"performance.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}