{"id":"https://openalex.org/W4290759903","doi":"https://doi.org/10.1080/09537325.2022.2110054","title":"Combining natural language processing techniques and algorithms LSA, word2vec and WMD for technological forecasting and similarity analysis in patent documents","display_name":"Combining natural language processing techniques and algorithms LSA, word2vec and WMD for technological forecasting and similarity analysis in patent documents","publication_year":2022,"publication_date":"2022-08-09","ids":{"openalex":"https://openalex.org/W4290759903","doi":"https://doi.org/10.1080/09537325.2022.2110054"},"language":"en","primary_location":{"id":"doi:10.1080/09537325.2022.2110054","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09537325.2022.2110054","pdf_url":null,"source":{"id":"https://openalex.org/S130699561","display_name":"Technology Analysis and Strategic Management","issn_l":"0953-7325","issn":["0953-7325","1465-3990"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Technology Analysis & Strategic Management","raw_type":"journal-article"},"type":"article","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/A5044511325","display_name":"Jo\u00e3o Marcos de Rezende","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160371","display_name":"Instituto Federal do Esp\u00edrito Santo","ror":"https://ror.org/05rshs160","country_code":"BR","type":"funder","lineage":["https://openalex.org/I4210160371"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Marcos de Rezende","raw_affiliation_strings":["Graduate Program in Applied Computing (PPComp), Federal Institute of Esp\u00edrito Santo (IFES), Serra, Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Applied Computing (PPComp), Federal Institute of Esp\u00edrito Santo (IFES), Serra, Brazil","institution_ids":["https://openalex.org/I4210160371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006998297","display_name":"Izabella Martins da Costa Rodrigues","orcid":"https://orcid.org/0000-0002-7458-9909"},"institutions":[{"id":"https://openalex.org/I4210160371","display_name":"Instituto Federal do Esp\u00edrito Santo","ror":"https://ror.org/05rshs160","country_code":"BR","type":"funder","lineage":["https://openalex.org/I4210160371"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Izabella Martins da Costa Rodrigues","raw_affiliation_strings":["Graduate Program in Applied Computing (PPComp), Federal Institute of Esp\u00edrito Santo (IFES), Serra, Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Applied Computing (PPComp), Federal Institute of Esp\u00edrito Santo (IFES), Serra, Brazil","institution_ids":["https://openalex.org/I4210160371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078629609","display_name":"Leandro Colombi Resendo","orcid":"https://orcid.org/0000-0001-7604-2440"},"institutions":[{"id":"https://openalex.org/I4210160371","display_name":"Instituto Federal do Esp\u00edrito Santo","ror":"https://ror.org/05rshs160","country_code":"BR","type":"funder","lineage":["https://openalex.org/I4210160371"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leandro Colombi Resendo","raw_affiliation_strings":["Graduate Program in Applied Computing (PPComp), Federal Institute of Esp\u00edrito Santo (IFES), Serra, Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Applied Computing (PPComp), Federal Institute of Esp\u00edrito Santo (IFES), Serra, Brazil","institution_ids":["https://openalex.org/I4210160371"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055174117","display_name":"Karin Satie Komati","orcid":"https://orcid.org/0000-0001-5677-4724"},"institutions":[{"id":"https://openalex.org/I4210160371","display_name":"Instituto Federal do Esp\u00edrito Santo","ror":"https://ror.org/05rshs160","country_code":"BR","type":"funder","lineage":["https://openalex.org/I4210160371"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Karin Satie Komati","raw_affiliation_strings":["Graduate Program in Applied Computing (PPComp), Federal Institute of Esp\u00edrito Santo (IFES), Serra, Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Applied Computing (PPComp), Federal Institute of Esp\u00edrito Santo (IFES), Serra, Brazil","institution_ids":["https://openalex.org/I4210160371"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006998297"],"corresponding_institution_ids":["https://openalex.org/I4210160371"],"apc_list":null,"apc_paid":null,"fwci":4.7685,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94296076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"36","issue":"8","first_page":"1695","last_page":"1716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10856","display_name":"Intellectual Property and Patents","score":0.9621999859809875,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10856","display_name":"Intellectual Property and Patents","score":0.9621999859809875,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14306","display_name":"Technology Assessment and Management","score":0.906000018119812,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.8821415901184082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7793060541152954},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.743035614490509},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5920231938362122},{"id":"https://openalex.org/keywords/trademark","display_name":"Trademark","score":0.5767438411712646},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.5064047574996948},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48679444193840027},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4681779444217682},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.44471338391304016},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4023611545562744},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3687974512577057},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.29001790285110474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2653965950012207},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.11248049139976501}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8821415901184082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793060541152954},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.743035614490509},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5920231938362122},{"id":"https://openalex.org/C2779027411","wikidata":"https://www.wikidata.org/wiki/Q167270","display_name":"Trademark","level":2,"score":0.5767438411712646},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.5064047574996948},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48679444193840027},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4681779444217682},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.44471338391304016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4023611545562744},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3687974512577057},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29001790285110474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2653965950012207},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.11248049139976501},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/09537325.2022.2110054","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09537325.2022.2110054","pdf_url":null,"source":{"id":"https://openalex.org/S130699561","display_name":"Technology Analysis and Strategic Management","issn_l":"0953-7325","issn":["0953-7325","1465-3990"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Technology Analysis & Strategic Management","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3315501189","display_name":null,"funder_award_id":"PROCESS: 2021-2S6CD","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G4258389934","display_name":null,"funder_award_id":"88887.568442/2020-00","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G4751498108","display_name":null,"funder_award_id":"308432/2020-7","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G8887375698","display_name":null,"funder_award_id":"FAPES 132/2021","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320323682","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa e Inova\u00e7\u00e3o do Esp\u00edrito Santo","ror":"https://ror.org/03cen2c33"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W341531820","https://openalex.org/W658020064","https://openalex.org/W2025701878","https://openalex.org/W2073344365","https://openalex.org/W2091612883","https://openalex.org/W2153579005","https://openalex.org/W2304774526","https://openalex.org/W2587990869","https://openalex.org/W2599307942","https://openalex.org/W2604272474","https://openalex.org/W2612044071","https://openalex.org/W2677871047","https://openalex.org/W2740284880","https://openalex.org/W2748006193","https://openalex.org/W2804530216","https://openalex.org/W2885850915","https://openalex.org/W2896685184","https://openalex.org/W2945487410","https://openalex.org/W2972726447","https://openalex.org/W2974226680","https://openalex.org/W3006232679","https://openalex.org/W3016677776","https://openalex.org/W3021303243","https://openalex.org/W3081886688","https://openalex.org/W3084357783","https://openalex.org/W3121856749","https://openalex.org/W3176028843","https://openalex.org/W3190383861","https://openalex.org/W6746241792"],"related_works":["https://openalex.org/W1994775821","https://openalex.org/W2012019886","https://openalex.org/W2091133150","https://openalex.org/W2945869148","https://openalex.org/W2398781203","https://openalex.org/W2009279505","https://openalex.org/W4206503171","https://openalex.org/W4366711670","https://openalex.org/W2558988915","https://openalex.org/W2972216353"],"abstract_inverted_index":{"Keyword":[0],"search":[1],"is":[2,17],"the":[3,27,38,53,59,74,77,106,121,130,159,175,182],"most":[4],"ordinary":[5],"tool":[6],"in":[7,147],"patent":[8,35,172],"offices;":[9],"however,":[10],"for":[11,34],"more":[12],"advanced":[13],"research,":[14],"free":[15],"software":[16],"not":[18],"presented":[19,178],"on":[20],"their":[21],"websites.":[22],"Thus,":[23],"this":[24],"paper":[25],"has":[26,49],"purpose":[28],"to":[29,98,119,126],"provide":[30],"a":[31,85,112],"data-mining":[32],"framework":[33],"documents,":[36],"linking":[37],"natural":[39],"language":[40],"processing":[41],"techniques":[42],"and":[43,58,67,80,94,168,174],"data":[44],"analysis":[45,54],"algorithms.":[46],"The":[47],"system":[48],"two":[50,108],"main":[51],"goals:":[52],"of":[55,61,76,114,132],"technological":[56],"prospection":[57],"evaluation":[60],"similarities":[62],"among":[63,134],"patents":[64,89],"through":[65],"titles":[66],"abstracts.":[68],"For":[69],"numerical":[70],"experiments,":[71],"we":[72,136],"used":[73],"base":[75],"US":[78],"Patent":[79],"Trademark":[81],"Office,":[82],"with":[83,100,158],"over":[84],"million":[86],"documents.":[87],"Analysing":[88],"about":[90],"TFT-LCD,":[91],"Flash":[92],"Memory":[93],"PDA,":[95],"from":[96,124,181],"2010":[97,125],"2018,":[99],"S-Curve":[101],"it":[102,116],"was":[103,117],"observed":[104],"that":[105,166],"last":[107],"technologies":[109],"decline.":[110],"Using":[111],"cloud":[113],"words,":[115],"possible":[118],"see":[120],"phone\u2019s":[122],"evolution,":[123],"2015.":[127],"To":[128],"evaluate":[129],"degree":[131],"similarity":[133],"patents,":[135],"investigated":[137],"Latent":[138],"Semantic":[139],"Analysis":[140],"(LSA),":[141],"Word2vec,":[142],"Word":[143],"Mover\u2019s":[144],"Distance":[145],"(WMD),":[146],"three":[148],"different":[149,179],"study":[150],"cases.":[151],"In":[152],"addition,":[153],"these":[154],"methods":[155],"were":[156],"compared":[157],"classical":[160],"Jaccard":[161,176],"index.":[162],"Numerical":[163],"results":[164],"show":[165],"LSA":[167],"WMD":[169],"obtained":[170],"similar":[171],"indications,":[173],"index":[177],"indications":[180],"other":[183],"three.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}