{"id":"https://openalex.org/W4402950130","doi":"https://doi.org/10.1007/s10844-024-00891-8","title":"A self-supervised seed-driven approach to topic modelling and clustering","display_name":"A self-supervised seed-driven approach to topic modelling and clustering","publication_year":2024,"publication_date":"2024-09-28","ids":{"openalex":"https://openalex.org/W4402950130","doi":"https://doi.org/10.1007/s10844-024-00891-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10844-024-00891-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-024-00891-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-024-00891-8.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10844-024-00891-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094215106","display_name":"Federico Ravenda","orcid":"https://orcid.org/0009-0004-1421-252X"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Federico Ravenda","raw_affiliation_strings":["Faculty of Informatics, Universit\u00e1 della Svizzera italiana, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Universit\u00e1 della Svizzera italiana, Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017310157","display_name":"Seyed Ali Bahrainian","orcid":"https://orcid.org/0000-0003-2860-5346"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Seyed Ali Bahrainian","raw_affiliation_strings":["Computer Science Department, University of Tuebingen, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Tuebingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059180331","display_name":"Andrea Raballo","orcid":"https://orcid.org/0000-0003-3709-4111"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Andrea Raballo","raw_affiliation_strings":["Faculty of Biomedical Sciences, Universit\u00e1 della Svizzera italiana, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Biomedical Sciences, Universit\u00e1 della Svizzera italiana, Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030873840","display_name":"Antonietta Mira","orcid":"https://orcid.org/0000-0002-5609-7935"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]},{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH","IT"],"is_corresponding":true,"raw_author_name":"Antonietta Mira","raw_affiliation_strings":["Department of Science and High Technology, Insubria University, Varese, Italy","Faculty of Economics, Universit\u00e1 della Svizzera italiana, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Science and High Technology, Insubria University, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]},{"raw_affiliation_string":"Faculty of Economics, Universit\u00e1 della Svizzera italiana, Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012367814","display_name":"F\u00e1bio Crestani","orcid":"https://orcid.org/0000-0001-8672-0700"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Fabio Crestani","raw_affiliation_strings":["Faculty of Informatics, Universit\u00e1 della Svizzera italiana, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Universit\u00e1 della Svizzera italiana, Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012367814","https://openalex.org/A5017310157","https://openalex.org/A5030873840","https://openalex.org/A5059180331","https://openalex.org/A5094215106"],"corresponding_institution_ids":["https://openalex.org/I115752224","https://openalex.org/I57201433","https://openalex.org/I8087733"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":1.9209,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87647231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"63","issue":"1","first_page":"333","last_page":"353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9980999827384949,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9904000163078308,"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":0.879749059677124},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6798005104064941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44287344813346863},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3731987476348877},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3627030849456787},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34977108240127563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.879749059677124},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6798005104064941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44287344813346863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3731987476348877},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3627030849456787},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34977108240127563}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10844-024-00891-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-024-00891-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-024-00891-8.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:irinsubria.uninsubria.it:11383/2184535","is_oa":false,"landing_page_url":"https://hdl.handle.net/11383/2184535","pdf_url":null,"source":{"id":"https://openalex.org/S4377196351","display_name":"IrInSubria (University of Insubria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115752224","host_organization_name":"University of Insubria","host_organization_lineage":["https://openalex.org/I115752224"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10844-024-00891-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-024-00891-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-024-00891-8.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F258283056","display_name":"Universit\u00e0 Della Svizzera Italiana","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402950130.pdf","grobid_xml":"https://content.openalex.org/works/W4402950130.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1970379189","https://openalex.org/W2010955400","https://openalex.org/W2105617746","https://openalex.org/W2131744502","https://openalex.org/W2138615112","https://openalex.org/W2159426623","https://openalex.org/W2250533720","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2621133045","https://openalex.org/W2768348081","https://openalex.org/W2789730224","https://openalex.org/W2803437449","https://openalex.org/W2896457183","https://openalex.org/W2907254481","https://openalex.org/W2911815954","https://openalex.org/W2911964244","https://openalex.org/W2962998311","https://openalex.org/W2968713397","https://openalex.org/W2970641574","https://openalex.org/W2976818350","https://openalex.org/W3007539960","https://openalex.org/W3021053579","https://openalex.org/W3044788535","https://openalex.org/W3045464143","https://openalex.org/W3135143565","https://openalex.org/W3155457426","https://openalex.org/W3156450083","https://openalex.org/W3176380929","https://openalex.org/W3216660278","https://openalex.org/W4205945237","https://openalex.org/W4221014796","https://openalex.org/W4233135949","https://openalex.org/W4235169531","https://openalex.org/W4311614307","https://openalex.org/W4312463050","https://openalex.org/W4322766399","https://openalex.org/W4323706304","https://openalex.org/W4386363413","https://openalex.org/W4389520455","https://openalex.org/W4391218191","https://openalex.org/W6639619044","https://openalex.org/W6680012447","https://openalex.org/W6682494755"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Abstract":[0],"Topic":[1],"models":[2,128],"are":[3],"useful":[4],"tools":[5],"for":[6,38],"extracting":[7,106],"the":[8,32,36],"most":[9],"salient":[10],"themes":[11],"within":[12],"a":[13,47,56,63,69,76,79,90],"collection":[14],"of":[15,23,35,92,94,105,131],"documents,":[16],"grouping":[17],"them":[18],"to":[19,51,73],"construct":[20],"clusters":[21,28],"representative":[22],"each":[24],"specific":[25],"topic.":[26],"These":[27],"summarize":[29],"and":[30,65,81,97,123,134],"represent":[31],"semantic":[33],"contents":[34],"documents":[37],"better":[39],"document":[40,80],"interpretation.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,61],"present":[46],"light":[48],"approach":[49,72],"able":[50],"learn":[52],"topic":[53,125],"representations":[54],"in":[55,129],"Self-Supervised":[57],"fashion.":[58],"More":[59],"specifically,":[60],"propose":[62],"lightweight":[64],"scalable":[66],"architecture":[67],"using":[68],"seed-word":[70],"driven":[71],"simultaneously":[74],"co-learn":[75],"representation":[77],"from":[78],"its":[82],"corresponding":[83],"word":[84],"embeddings.":[85],"The":[86],"results":[87],"obtained":[88],"on":[89,112],"variety":[91],"datasets":[93,115],"different":[95,132],"sizes":[96],"natures":[98],"show":[99],"that":[100,117],"our":[101,110,118],"model":[102,119],"is":[103],"capable":[104],"meaningful":[107],"topics.":[108],"Furthermore,":[109],"experiments":[111],"five":[113],"benchmark":[114],"illustrate":[116],"outperforms":[120],"both":[121],"traditional":[122],"neural":[124],"modelling":[126],"baseline":[127],"terms":[130],"coherence":[133],"clustering":[135],"accuracy":[136],"measures.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}