{"id":"https://openalex.org/W2175351445","doi":"https://doi.org/10.1109/fuzz-ieee.2015.7337892","title":"Text based classification of companies in CrunchBase","display_name":"Text based classification of companies in CrunchBase","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2175351445","doi":"https://doi.org/10.1109/fuzz-ieee.2015.7337892","mag":"2175351445"},"language":"en","primary_location":{"id":"doi:10.1109/fuzz-ieee.2015.7337892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz-ieee.2015.7337892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10071/25098","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090633243","display_name":"Fernando Batista","orcid":"https://orcid.org/0000-0002-1075-0177"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Fernando Batista","raw_affiliation_strings":["INESC-ID, ISCTE-Instituto Universit\u00e1rio de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"INESC-ID, ISCTE-Instituto Universit\u00e1rio de Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029618080","display_name":"Jo\u00e3o Paulo Carvalho","orcid":"https://orcid.org/0000-0003-0005-8299"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]},{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joao Paulo Carvalho","raw_affiliation_strings":["INESC-ID, Instituto Superior Tecnico-Universidade de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"INESC-ID, Instituto Superior Tecnico-Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090633243"],"corresponding_institution_ids":["https://openalex.org/I121345201"],"apc_list":null,"apc_paid":null,"fwci":2.1572,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90240912,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"322","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991000294685364,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9991000294685364,"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":0.9979000091552734,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.789642333984375},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.6932586431503296},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5636739730834961},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5216884016990662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5190887451171875},{"id":"https://openalex.org/keywords/fuzzy-set","display_name":"Fuzzy set","score":0.5145861506462097},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5114211440086365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3891603946685791},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37548595666885376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3535482883453369}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789642333984375},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.6932586431503296},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5636739730834961},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5216884016990662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5190887451171875},{"id":"https://openalex.org/C42011625","wikidata":"https://www.wikidata.org/wiki/Q1055058","display_name":"Fuzzy set","level":3,"score":0.5145861506462097},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5114211440086365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3891603946685791},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37548595666885376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3535482883453369},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/fuzz-ieee.2015.7337892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz-ieee.2015.7337892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositorio.iscte-iul.pt:10071/25098","is_oa":true,"landing_page_url":"http://hdl.handle.net/10071/25098","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"","raw_type":null}],"best_oa_location":{"id":"pmh:oai:repositorio.iscte-iul.pt:10071/25098","is_oa":true,"landing_page_url":"http://hdl.handle.net/10071/25098","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"","raw_type":null},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1211014924","https://openalex.org/W1512098439","https://openalex.org/W1550206324","https://openalex.org/W1600036847","https://openalex.org/W1604513186","https://openalex.org/W1973953796","https://openalex.org/W1978394996","https://openalex.org/W2008513264","https://openalex.org/W2024228866","https://openalex.org/W2067742205","https://openalex.org/W2084424085","https://openalex.org/W2100432176","https://openalex.org/W2122743328","https://openalex.org/W2130383384","https://openalex.org/W2137349054","https://openalex.org/W2151040995","https://openalex.org/W2154359981","https://openalex.org/W2166706824","https://openalex.org/W2251939518","https://openalex.org/W2280726098","https://openalex.org/W6627915109","https://openalex.org/W6630527977","https://openalex.org/W6632865047","https://openalex.org/W6678176756","https://openalex.org/W6679303276","https://openalex.org/W6682839988","https://openalex.org/W6691459498"],"related_works":["https://openalex.org/W2339806289","https://openalex.org/W3008853525","https://openalex.org/W2368132270","https://openalex.org/W2173185020","https://openalex.org/W2946784807","https://openalex.org/W2986003362","https://openalex.org/W109501413","https://openalex.org/W2075134888","https://openalex.org/W4388857868","https://openalex.org/W2157505264"],"abstract_inverted_index":{"This":[0,27],"paper":[1],"introduces":[2],"two":[3],"fuzzy":[4,130],"fingerprint":[5,131],"based":[6,20,132],"text":[7,114],"classification":[8,115],"techniques":[9,116],"that":[10,51,75],"were":[11],"successfully":[12],"applied":[13,124],"to":[14,36,48,58,119,125],"automatically":[15],"label":[16],"companies":[17],"from":[18],"CrunchBase,":[19],"purely":[21],"on":[22],"their":[23],"unstructured":[24],"textual":[25,53],"description.":[26],"is":[28,107],"a":[29,71,96,105],"real":[30],"and":[31,46,63,92],"very":[32,97],"challenging":[33],"problem":[34],"due":[35],"the":[37,49,52,87,103,112,126,129,135],"large":[38,98],"set":[39],"of":[40,89,100,111],"possible":[41],"labels":[42],"(more":[43],"than":[44],"40)":[45],"also":[47],"fact":[50],"descriptions":[54],"do":[55],"not":[56],"have":[57],"abide":[59],"by":[60],"any":[61],"criteria":[62],"are,":[64],"therefore,":[65],"extremely":[66],"heterogeneous.":[67],"Fuzzy":[68],"fingerprints":[69],"are":[70],"recently":[72],"introduced":[73],"technique":[74],"can":[76,93],"be":[77],"used":[78,118],"for":[79],"performing":[80],"fast":[81],"classification.":[82],"They":[83],"perform":[84],"well":[85],"in":[86],"presence":[88],"unbalanced":[90],"datasets":[91],"cope":[94],"with":[95],"number":[99],"classes.":[101],"In":[102],"paper,":[104],"comparison":[106],"performed":[108],"against":[109],"some":[110],"best":[113],"commonly":[117],"address":[120],"similar":[121],"problems.":[122],"When":[123],"CrunchBase":[127],"dataset,":[128],"approach":[133],"outperformed":[134],"other":[136],"techniques.":[137]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}