{"id":"https://openalex.org/W4407738243","doi":"https://doi.org/10.1007/s41109-025-00693-z","title":"Statistically validated network for analysing textual data","display_name":"Statistically validated network for analysing textual data","publication_year":2025,"publication_date":"2025-02-19","ids":{"openalex":"https://openalex.org/W4407738243","doi":"https://doi.org/10.1007/s41109-025-00693-z"},"language":"en","primary_location":{"id":"doi:10.1007/s41109-025-00693-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41109-025-00693-z","pdf_url":"https://appliednetsci.springeropen.com/counter/pdf/10.1007/s41109-025-00693-z","source":{"id":"https://openalex.org/S3035517252","display_name":"Applied Network Science","issn_l":"2364-8228","issn":["2364-8228"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"Applied Network Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://appliednetsci.springeropen.com/counter/pdf/10.1007/s41109-025-00693-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101546479","display_name":"Andrea Simonetti","orcid":"https://orcid.org/0009-0003-3594-6656"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Andrea Simonetti","raw_affiliation_strings":["Department of Economics, Business, and Statistics, University of Palermo, Viale delle Scienze, Ed. 13, 90128, Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Economics, Business, and Statistics, University of Palermo, Viale delle Scienze, Ed. 13, 90128, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088371040","display_name":"Alessandro Albano","orcid":"https://orcid.org/0000-0002-4259-0710"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Albano","raw_affiliation_strings":["Department of Economics, Business, and Statistics, University of Palermo, Viale delle Scienze, Ed. 13, 90128, Palermo, Italy","Sustainable Mobility Center (Centro Nazionale per la Mobilit\u00e0 Sostenibile-CNMS), Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Economics, Business, and Statistics, University of Palermo, Viale delle Scienze, Ed. 13, 90128, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]},{"raw_affiliation_string":"Sustainable Mobility Center (Centro Nazionale per la Mobilit\u00e0 Sostenibile-CNMS), Milan, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032380303","display_name":"Michele Tumminello","orcid":"https://orcid.org/0000-0001-6045-6761"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Tumminello","raw_affiliation_strings":["Department of Economics, Business, and Statistics, University of Palermo, Viale delle Scienze, Ed. 13, 90128, Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Economics, Business, and Statistics, University of Palermo, Viale delle Scienze, Ed. 13, 90128, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035375830","display_name":"Tiziana Di Matteo","orcid":"https://orcid.org/0000-0002-5913-3268"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I4210108754","display_name":"Centro Ricerche Enrico Fermi","ror":"https://ror.org/01qb1sw63","country_code":"IT","type":"archive","lineage":["https://openalex.org/I4210108754"]},{"id":"https://openalex.org/I4210112164","display_name":"Complexity Science Hub","ror":"https://ror.org/023dz9m50","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I4210112164"]}],"countries":["AT","GB","IT"],"is_corresponding":false,"raw_author_name":"T. Di Matteo","raw_affiliation_strings":["Centro Ricerche Enrico Fermi, Via Panisperna 89A, 00184, Rome, Italy","Complexity Science Hub Vienna, Josefst\u00e4dter Stra\u00dfe 39, 1080, Vienna, Austria","Department of Mathematics, King\u2019s College London, The Strand, London, WC2R 2LS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro Ricerche Enrico Fermi, Via Panisperna 89A, 00184, Rome, Italy","institution_ids":["https://openalex.org/I4210108754"]},{"raw_affiliation_string":"Complexity Science Hub Vienna, Josefst\u00e4dter Stra\u00dfe 39, 1080, Vienna, Austria","institution_ids":["https://openalex.org/I4210112164"]},{"raw_affiliation_string":"Department of Mathematics, King\u2019s College London, The Strand, London, WC2R 2LS, UK","institution_ids":["https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101546479"],"corresponding_institution_ids":["https://openalex.org/I900890020"],"apc_list":{"value":790,"currency":"GBP","value_usd":969},"apc_paid":{"value":790,"currency":"GBP","value_usd":969},"fwci":2.0776,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86850443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"10","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9962000250816345,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9962000250816345,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9638000130653381,"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":0.44753196835517883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38613981008529663},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3208869993686676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44753196835517883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38613981008529663},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3208869993686676}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s41109-025-00693-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41109-025-00693-z","pdf_url":"https://appliednetsci.springeropen.com/counter/pdf/10.1007/s41109-025-00693-z","source":{"id":"https://openalex.org/S3035517252","display_name":"Applied Network Science","issn_l":"2364-8228","issn":["2364-8228"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"Applied Network Science","raw_type":"journal-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/f5349a48-e258-4d73-b4a6-6120b1a01c64","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/f5349a48-e258-4d73-b4a6-6120b1a01c64","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Simonetti, A, Albano, A, Tumminello, M & Di Matteo, T 2025, 'Statistically validated network for analysing textual data', Applied Network Science, vol. 10, no. 1. https://doi.org/10.1007/s41109-025-00693-z","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:3d9c66e982e54bc1b1a5a9120bc02d10","is_oa":false,"landing_page_url":"https://doaj.org/article/3d9c66e982e54bc1b1a5a9120bc02d10","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Network Science, Vol 10, Iss 1, Pp 1-29 (2025)","raw_type":"article"},{"id":"pmh:oai:iris.unipa.it:10447/673424","is_oa":true,"landing_page_url":"https://hdl.handle.net/10447/673424","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","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":"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/s41109-025-00693-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41109-025-00693-z","pdf_url":"https://appliednetsci.springeropen.com/counter/pdf/10.1007/s41109-025-00693-z","source":{"id":"https://openalex.org/S3035517252","display_name":"Applied Network Science","issn_l":"2364-8228","issn":["2364-8228"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"Applied Network Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1717723436","display_name":null,"funder_award_id":"PE00000018","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1924511797","display_name":null,"funder_award_id":"1033-17/06/2022","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3478515953","display_name":null,"funder_award_id":"CN00000023","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4605703711","display_name":null,"funder_award_id":"CUP B73C22001260006","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6977740132","display_name":null,"funder_award_id":"CN00000023","funder_id":"https://openalex.org/F7311471023","funder_display_name":"NextGenerationEU"},{"id":"https://openalex.org/G8060328387","display_name":null,"funder_award_id":"GRINS PE00000018","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8597753631","display_name":null,"funder_award_id":"PE00000018","funder_id":"https://openalex.org/F7311471023","funder_display_name":"NextGenerationEU"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F7311471023","display_name":"NextGenerationEU","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407738243.pdf","grobid_xml":"https://content.openalex.org/works/W4407738243.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W745973578","https://openalex.org/W1596515083","https://openalex.org/W1972675431","https://openalex.org/W1981467090","https://openalex.org/W1988428986","https://openalex.org/W2008404183","https://openalex.org/W2034274945","https://openalex.org/W2036731102","https://openalex.org/W2038043464","https://openalex.org/W2048176942","https://openalex.org/W2048488939","https://openalex.org/W2054658115","https://openalex.org/W2087459024","https://openalex.org/W2090372231","https://openalex.org/W2102907934","https://openalex.org/W2110065044","https://openalex.org/W2119998616","https://openalex.org/W2126843316","https://openalex.org/W2127048411","https://openalex.org/W2131681506","https://openalex.org/W2151703435","https://openalex.org/W2300469216","https://openalex.org/W2531871281","https://openalex.org/W2592771984","https://openalex.org/W2742276251","https://openalex.org/W2897249806","https://openalex.org/W2901715397","https://openalex.org/W2982783034","https://openalex.org/W3034238904","https://openalex.org/W3098885419","https://openalex.org/W3099768174","https://openalex.org/W3102641634","https://openalex.org/W3103006263","https://openalex.org/W3104955266","https://openalex.org/W3106188259","https://openalex.org/W3123545922","https://openalex.org/W3151006805","https://openalex.org/W3173187313","https://openalex.org/W3174776221","https://openalex.org/W4283696141","https://openalex.org/W4312203457","https://openalex.org/W4317538208"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Abstract":[0],"This":[1,23],"paper":[2],"presents":[3],"a":[4,29,98,116],"novel":[5],"methodology,":[6],"called":[7],"Word":[8],"Co-occurrence":[9],"SVN":[10],"topic":[11,18,142],"model":[12],"(WCSVNtm),":[13],"for":[14,189],"document":[15,48,145,178],"clustering":[16],"and":[17,34,47,71,115,144,155,177],"modeling":[19,143],"in":[20,138,194],"textual":[21],"datasets.":[22],"method":[24],"represents":[25],"the":[26,39,56,62,89,104,123,139,148,173],"corpus":[27],"as":[28,73],"bipartite":[30],"network":[31],"of":[32,42,66,91,100,109,119,141,175],"words":[33,67],"documents":[35,46,76,121],"to":[36,61],"rigorously":[37],"assess":[38],"statistical":[40],"significance":[41],"word":[43],"co-occurrences":[44],"within":[45],"overlap":[49],"based":[50,82],"on":[51,83],"shared":[52],"vocabulary.":[53],"By":[54],"employing":[55],"Leiden":[57],"community":[58,195],"detection":[59,196],"algorithm":[60],"SVN,":[63],"distinct":[64],"communities":[65],"can":[68,77],"be":[69,78],"identified":[70],"interpreted":[72],"topics.":[74],"Similarly,":[75],"sorted":[79],"into":[80],"groups":[81],"their":[84],"thematic":[85],"similarities.":[86],"We":[87],"demonstrate":[88],"effectiveness":[90],"our":[92,128,132,201],"approach":[93,133],"by":[94],"analyzing":[95],"three":[96],"datasets:":[97],"set":[99],"120":[101],"Wikipedia":[102],"articles,":[103],"arXiv10":[105],"dataset,":[106],"which":[107],"consists":[108],"100,000":[110],"abstracts":[111],"from":[112,122],"scientific":[113],"papers,":[114],"sampled":[117],"subset":[118],"10,000":[120],"original":[124],"arXiv10.":[125],"To":[126],"benchmark":[127],"results,":[129],"we":[130],"compare":[131],"with":[134],"several":[135],"well-established":[136],"models":[137],"field":[140],"clustering,":[146],"including":[147],"hierarchical":[149],"Stochastic":[150],"Block":[151],"Model":[152],"(hSBM),":[153],"BERTopic,":[154],"Latent":[156],"Dirichlet":[157],"Allocation":[158],"(LDA).":[159],"The":[160],"results":[161],"show":[162],"that":[163],"WCSVNtm":[164],"achieves":[165],"competitive":[166],"performance":[167],"across":[168],"all":[169],"datasets,":[170],"automatically":[171],"selecting":[172],"number":[174],"topics":[176],"clusters,":[179],"whereas":[180],"state-of-the-art":[181],"methods":[182],"require":[183],"prior":[184],"knowledge":[185],"or":[186],"additional":[187],"tuning":[188],"optimization.":[190],"Finally,":[191],"any":[192],"advancements":[193],"algorithms":[197],"could":[198],"further":[199],"improve":[200],"method.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}