{"id":"https://openalex.org/W3089073069","doi":null,"title":"Multiclass Text Classification on Unbalanced, Sparse and Noisy Data","display_name":"Multiclass Text Classification on Unbalanced, Sparse and Noisy Data","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W3089073069","mag":"3089073069"},"language":"en","primary_location":{"id":"pmh:oai:dspace.ut.ee:10062/93040","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10062/93040","pdf_url":"https://dspace.ut.ee/bitstreams/7eb8e2f2-7764-464f-a586-1a41f93f7159/download","source":{"id":"https://openalex.org/S4306401412","display_name":"DSpace repository (University of Tartu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I56085075","host_organization_name":"University of Tartu","host_organization_lineage":["https://openalex.org/I56085075"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.ut.ee/bitstreams/7eb8e2f2-7764-464f-a586-1a41f93f7159/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049731694","display_name":"Matthias Damaschk","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Damaschk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070034057","display_name":"Tillmann D\u00f6nicke","orcid":"https://orcid.org/0000-0001-5844-9167","observed_orcids":["https://orcid.org/0000-0001-5844-9167"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tillmann D\u00f6nicke","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5844-9167","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078880407","display_name":"Florian Lux","orcid":"https://orcid.org/0000-0003-4325-5129","observed_orcids":["https://orcid.org/0000-0003-4325-5129"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Lux","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4325-5129","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8013,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.75327689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9731000065803528,"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":0.9731000065803528,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.015599999576807022,"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":0.00559999980032444,"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/multi-class-text-classification","display_name":"multi-class text classification","score":0.9729999899864197},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.8629999756813049},{"id":"https://openalex.org/keywords/noisy-data","display_name":"noisy data","score":0.7929999828338623},{"id":"https://openalex.org/keywords/data-sparsity","display_name":"data sparsity","score":0.8040000200271606},{"id":"https://openalex.org/keywords/neural-network-classifier","display_name":"neural network classifier","score":0.718999981880188},{"id":"https://openalex.org/keywords/song-lyrics","display_name":"song lyrics","score":0.5260000228881836},{"id":"https://openalex.org/keywords/artist-recognition","display_name":"artist identification","score":0.7139999866485596},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.6209999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733108401298523},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6673420667648315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6445186138153076},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.6316790580749512},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5957847237586975},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.5835732817649841},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5588607788085938},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5462840795516968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47717538475990295},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4587209224700928},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3840513527393341},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.13772284984588623},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07270976901054382},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:dspace.ut.ee:10062/93040","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10062/93040","pdf_url":"https://dspace.ut.ee/bitstreams/7eb8e2f2-7764-464f-a586-1a41f93f7159/download","source":{"id":"https://openalex.org/S4306401412","display_name":"DSpace repository (University of Tartu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I56085075","host_organization_name":"University of Tartu","host_organization_lineage":["https://openalex.org/I56085075"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/131445","doi":null,"is_oa":true,"landing_page_url":"https://aclanthology.org/W19-6207/","pdf_url":"https://aclanthology.org/W19-6207.pdf","source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:3089073069","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/W19-6207.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:dspace.ut.ee:10062/93040","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10062/93040","pdf_url":"https://dspace.ut.ee/bitstreams/7eb8e2f2-7764-464f-a586-1a41f93f7159/download","source":{"id":"https://openalex.org/S4306401412","display_name":"DSpace repository (University of Tartu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I56085075","host_organization_name":"University of Tartu","host_organization_lineage":["https://openalex.org/I56085075"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325850","display_name":"Universit\u00e4t Stuttgart","ror":"https://ror.org/04vnq7t77"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3089073069.pdf","grobid_xml":"https://content.openalex.org/works/W3089073069.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W131896369","https://openalex.org/W1614298861","https://openalex.org/W2014545475","https://openalex.org/W2040870580","https://openalex.org/W2095705004","https://openalex.org/W2131744502","https://openalex.org/W2138302120","https://openalex.org/W2265846598","https://openalex.org/W2297405797","https://openalex.org/W2766736793","https://openalex.org/W2963908732"],"related_works":["https://openalex.org/W2942499619","https://openalex.org/W4413810116","https://openalex.org/W4282832385","https://openalex.org/W4390441065","https://openalex.org/W2357983927","https://openalex.org/W3199746621","https://openalex.org/W2936668548","https://openalex.org/W2354551786","https://openalex.org/W1974840771","https://openalex.org/W3147762595"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"methods":[3,40],"to":[4,16,19,47,58],"improve":[5],"the":[6,59,73],"performance":[7],"of":[8,23,30],"text":[9],"classification":[10,77],"on":[11],"data":[12],"that":[13,61],"is":[14,52,84],"difficult":[15],"classify":[17],"due":[18],"a":[20,48,76,85],"large":[21],"number":[22],"unbalanced":[24,54],"classes":[25],"with":[26,36,41,80],"noisy":[27],"examples.A":[28],"variety":[29],"features":[31],"are":[32,45],"tested,":[33],"in":[34],"combination":[35],"three":[37],"different":[38],"neural-network-based":[39],"increasing":[42],"complexity.The":[43],"classifiers":[44],"applied":[46],"songtext-artist":[49],"dataset":[50],"which":[51],"large,":[53],"and":[55,70],"noisy.We":[56],"come":[57],"conclusion":[60],"substantial":[62],"improvement":[63],"can":[64],"be":[65],"obtained":[66],"by":[67],"removing":[68],"unbalancedness":[69],"sparsity":[71],"from":[72],"data.This":[74],"fulfils":[75],"task":[78],"unsatisfactorily-however,":[79],"contemporary":[81],"methods,":[82],"it":[83],"practical":[86],"step":[87],"towards":[88],"fairly":[89],"satisfactory":[90],"results.":[91]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-10-01T00:00:00"}