{"id":"https://openalex.org/W4210347189","doi":"https://doi.org/10.1145/3503516.3503527","title":"Document Clustering vs Topic Models: A Case Study","display_name":"Document Clustering vs Topic Models: A Case Study","publication_year":2021,"publication_date":"2021-12-09","ids":{"openalex":"https://openalex.org/W4210347189","doi":"https://doi.org/10.1145/3503516.3503527"},"language":"en","primary_location":{"id":"doi:10.1145/3503516.3503527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503516.3503527","pdf_url":null,"source":{"id":"https://openalex.org/S4306417788","display_name":"Australasian Document Computing Symposium","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Australasian Document Computing Symposium","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102859794","display_name":"Meng Yuan","orcid":"https://orcid.org/0000-0002-6291-6896"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Meng Yuan","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pauline Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Pauline Lin","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":0.767,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73160727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9962999820709229,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9962999820709229,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9962999820709229,"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/T11106","display_name":"Data Management and Algorithms","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.6560288667678833},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.584371030330658},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.41599780321121216},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3832138180732727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2767544984817505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560288667678833},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.584371030330658},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.41599780321121216},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3832138180732727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2767544984817505}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503516.3503527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503516.3503527","pdf_url":null,"source":{"id":"https://openalex.org/S4306417788","display_name":"Australasian Document Computing Symposium","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Australasian Document Computing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W2000117996","https://openalex.org/W2011430131","https://openalex.org/W2041565863","https://openalex.org/W2046878543","https://openalex.org/W2087743880","https://openalex.org/W2155194165","https://openalex.org/W2420602380","https://openalex.org/W2790740913","https://openalex.org/W2887229810","https://openalex.org/W2938824800","https://openalex.org/W3157575185","https://openalex.org/W4210651385","https://openalex.org/W4213009331","https://openalex.org/W4230572649","https://openalex.org/W4308947196"],"related_works":["https://openalex.org/W1834608617","https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2101955803","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2380998760","https://openalex.org/W2357241418","https://openalex.org/W2370554703","https://openalex.org/W2354429408"],"abstract_inverted_index":{"Document":[0],"collections":[1,17,103],"can":[2],"be":[3,27],"characterised":[4],"in":[5,37,66,81,93,116],"a":[6,67,71],"variety":[7],"of":[8,39,42,70,101,127],"ways.":[9],"Two":[10],"key":[11],"approaches":[12,118],"are":[13,45,96,107],"clustering,":[14],"which":[15,33,94],"partitions":[16],"into":[18],"subcollections":[19],"with":[20],"the":[21,24,35,58,89,99,102,125],"expectation":[22],"that":[23,44,78,104],"contents":[25,36,126],"will":[26],"thematically":[28],"linked,":[29],"and":[30,63,123],"topic":[31,64],"models,":[32],"describe":[34],"terms":[38],"weighted":[40],"lists":[41],"words":[43],"expected":[46],"to":[47],"represent":[48],"different":[49,91],"themes.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"report":[55],"experiments":[56],"on":[57],"observed":[59],"relationship":[60],"between":[61],"clusters":[62],"models":[65],"preliminary":[68],"study":[69],"large":[72],"text":[73],"collection.":[74],"Both":[75],"produce":[76],"results":[77],"appear":[79],"cohesive":[80],"their":[82],"own":[83],"right,":[84],"but":[85],"surprisingly":[86],"\u2013":[87,98],"given":[88],"very":[90],"ways":[92],"they":[95,105],"formed":[97],"descriptions":[100],"generate":[106],"strongly":[108],"similar.":[109],"This":[110],"unexpected":[111],"mutual":[112],"reinforcement":[113],"creates":[114],"confidence":[115],"both":[117],"as":[119],"tools":[120],"for":[121],"annotating":[122],"describing":[124],"document":[128],"collections.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}