{"id":"https://openalex.org/W3028148433","doi":"https://doi.org/10.1145/3383583.3398529","title":"Classification and Clustering of arXiv Documents, Sections, and Abstracts, Comparing Encodings of Natural and Mathematical Language","display_name":"Classification and Clustering of arXiv Documents, Sections, and Abstracts, Comparing Encodings of Natural and Mathematical Language","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3028148433","doi":"https://doi.org/10.1145/3383583.3398529","mag":"3028148433"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.11021","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Philipp Scharpf","orcid":null},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Philipp Scharpf","raw_affiliation_strings":["University of Konstanz, Konstanz, Germany"],"affiliations":[{"raw_affiliation_string":"University of Konstanz, Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Moritz Schubotz","orcid":null},"institutions":[{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz Schubotz","raw_affiliation_strings":["University of Wuppertal & FIZ Karlsruhe, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"University of Wuppertal & FIZ Karlsruhe, Karlsruhe, Germany","institution_ids":["https://openalex.org/I167360494"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Abdou Youssef","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdou Youssef","raw_affiliation_strings":["George Washington University, Washington, WA, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, WA, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Felix Hamborg","orcid":null},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Hamborg","raw_affiliation_strings":["University of Konstanz, Konstanz, Germany"],"affiliations":[{"raw_affiliation_string":"University of Konstanz, Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Norman Meuschke","orcid":null},"institutions":[{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]},{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Norman Meuschke","raw_affiliation_strings":["University of Wuppertal & University of Konstanz, Wuppertal, Germany"],"affiliations":[{"raw_affiliation_string":"University of Wuppertal & University of Konstanz, Wuppertal, Germany","institution_ids":["https://openalex.org/I167360494","https://openalex.org/I189712700"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bela Gipp","orcid":null},"institutions":[{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]},{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bela Gipp","raw_affiliation_strings":["University of Wuppertal & University of Konstanz, Wuppertal, Germany"],"affiliations":[{"raw_affiliation_string":"University of Wuppertal & University of Konstanz, Wuppertal, Germany","institution_ids":["https://openalex.org/I167360494","https://openalex.org/I189712700"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189712700"],"apc_list":null,"apc_paid":null,"fwci":1.2995,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84676504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9926999807357788,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7735999822616577},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6269000172615051},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49810001254081726},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4262999892234802},{"id":"https://openalex.org/keywords/preprint","display_name":"Preprint","score":0.3837999999523163},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.34549999237060547},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.323199987411499},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.3181999921798706}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7735999822616577},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6269000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6227999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5368000268936157},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41769999265670776},{"id":"https://openalex.org/C43169469","wikidata":"https://www.wikidata.org/wiki/Q580922","display_name":"Preprint","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3140000104904175},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.27469998598098755},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C34872919","wikidata":"https://www.wikidata.org/wiki/Q7092302","display_name":"One-class classification","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C172347087","wikidata":"https://www.wikidata.org/wiki/Q3217196","display_name":"Language of mathematics","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3383583.3398529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.11021","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.11021","pdf_url":"https://arxiv.org/pdf/2005.11021","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"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/106674","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/106674","pdf_url":null,"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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"no"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.11021","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.11021","pdf_url":"https://arxiv.org/pdf/2005.11021","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1493584520","https://openalex.org/W1614298861","https://openalex.org/W1840435438","https://openalex.org/W2001771035","https://openalex.org/W2009957709","https://openalex.org/W2031976076","https://openalex.org/W2080133951","https://openalex.org/W2118020653","https://openalex.org/W2123442489","https://openalex.org/W2169818249","https://openalex.org/W2182868890","https://openalex.org/W2285555962","https://openalex.org/W2316340232","https://openalex.org/W2396820472","https://openalex.org/W2397622830","https://openalex.org/W2407793991","https://openalex.org/W2802787326","https://openalex.org/W2883611677","https://openalex.org/W2883885170","https://openalex.org/W2884001105","https://openalex.org/W2887888371","https://openalex.org/W2896457183","https://openalex.org/W2965221296","https://openalex.org/W2997591727","https://openalex.org/W3089116201","https://openalex.org/W4236521339"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,26],"paper,":[2],"we":[3,143,156],"show":[4,144],"how":[5],"selecting":[6],"and":[7,12,17,33,58,60,64,69,80,93,108,117,119,131,140,158,162],"combining":[8],"encodings":[9,55,73],"of":[10,19,30,56,66,87,91,97,115,126],"natural":[11],"mathematical":[13,22],"language":[14],"affect":[15],"classification":[16,68,75,130,161],"clustering":[18,70,132],"documents":[20],"with":[21],"content.":[23],"We":[24,100],"demonstrate":[25],"by":[27,43],"using":[28],"sets":[29],"documents,":[31],"sections,":[32],"abstracts":[34],"from":[35],"the":[36,62,113,146],"arXiv":[37],"preprint":[38],"server":[39],"that":[40,145],"are":[41],"labeled":[42],"their":[44],"subject":[45],"class":[46],"(mathematics,":[47],"computer":[48,147],"science,":[49],"physics,":[50],"etc.)":[51],"to":[52,78,84],"compare":[53],"different":[54],"text":[57,107,116],"formulae":[59,118],"evaluate":[61,157],"performance":[63],"runtimes":[65],"selected":[67],"algorithms.":[71],"Our":[72],"achieve":[74],"accuracies":[76],"up":[77,83],"82.8%":[79],"cluster":[81],"purities":[82],"69.4%":[85],"(number":[86],"clusters":[88],"equals":[89],"number":[90,96],"classes),":[92],"99.9%":[94],"(unspecified":[95],"clusters)":[98],"respectively.":[99],"observe":[101],"a":[102,127,149],"relatively":[103],"low":[104],"correlation":[105],"between":[106],"math":[109],"similarity,":[110],"which":[111],"indicates":[112],"independence":[114],"motivates":[120],"treating":[121],"them":[122],"as":[123],"separate":[124],"features":[125],"document.":[128],"The":[129],"can":[133],"be":[134],"employed,":[135],"e.g.,":[136],"for":[137],"document":[138],"search":[139],"recommendation.":[141],"Furthermore,":[142],"outperforms":[148],"human":[150],"expert":[151],"when":[152],"classifying":[153],"documents.":[154],"Finally,":[155],"discuss":[159],"multi-label":[160],"formula":[163],"semantification.":[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":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-05-29T00:00:00"}