{"id":"https://openalex.org/W2136232777","doi":"https://doi.org/10.1145/1141753.1141766","title":"A comparative study of citations and links in document classification","display_name":"A comparative study of citations and links in document classification","publication_year":2006,"publication_date":"2006-06-11","ids":{"openalex":"https://openalex.org/W2136232777","doi":"https://doi.org/10.1145/1141753.1141766","mag":"2136232777"},"language":"en","primary_location":{"id":"doi:10.1145/1141753.1141766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-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/A5005484658","display_name":"Thierson Couto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thierson Couto","raw_affiliation_strings":["University of Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927757","display_name":"Marco Cristo","orcid":"https://orcid.org/0000-0001-8948-4192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Cristo","raw_affiliation_strings":["University of Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":["University of Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011911239","display_name":"P\u00e1vel Calado","orcid":"https://orcid.org/0000-0001-6478-229X"},"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":false,"raw_author_name":"P\u00e1vel Calado","raw_affiliation_strings":["IST/INESC-ID, Lisboa, Portugal","IST/INESC-ID Lisboa, Portugal#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IST/INESC-ID, Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"IST/INESC-ID Lisboa, Portugal#TAB#","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067195269","display_name":"N\u00edvio Ziviani","orcid":"https://orcid.org/0000-0002-7079-2010"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nivio Ziviani","raw_affiliation_strings":["University of Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015781017","display_name":"Edleno Silva de Moura","orcid":"https://orcid.org/0000-0002-7860-9575"},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edleno Moura","raw_affiliation_strings":["Federal University of Amazonas, Manaus, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Amazonas, Manaus, Brazil","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108556969","display_name":"Berthier Ribeiro\u2010Neto","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["BR","US"],"is_corresponding":false,"raw_author_name":"Berthier Ribeiro-Neto","raw_affiliation_strings":["Federal University Minas Gerais, Belo Horizonte, Brazil and Google Engineering, Belo Horizonte, Brazil","Federal University Minas Gerais, Belo Horizonte, Brazil and Google Engineering, Belo Horizonte, Brazil#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University Minas Gerais, Belo Horizonte, Brazil and Google Engineering, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Federal University Minas Gerais, Belo Horizonte, Brazil and Google Engineering, Belo Horizonte, Brazil#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.816,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.98370866,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9940999746322632,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9940999746322632,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9905999898910522,"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":0.9858999848365784,"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":0.8117748498916626},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.7809238433837891},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6867706775665283},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.6852482557296753},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.667331874370575},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6607675552368164},{"id":"https://openalex.org/keywords/bibliographic-coupling","display_name":"Bibliographic coupling","score":0.5376665592193604},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5372827649116516},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4146805703639984},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.37407541275024414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2783142328262329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117748498916626},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.7809238433837891},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6867706775665283},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.6852482557296753},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.667331874370575},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6607675552368164},{"id":"https://openalex.org/C2776822937","wikidata":"https://www.wikidata.org/wiki/Q856335","display_name":"Bibliographic coupling","level":3,"score":0.5376665592193604},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5372827649116516},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4146805703639984},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.37407541275024414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2783142328262329},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1141753.1141766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.121.4505","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.121.4505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.ufmg.br/~nivio/papers/jcdl06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W197400963","https://openalex.org/W1482260847","https://openalex.org/W1563243329","https://openalex.org/W1815110991","https://openalex.org/W1942958706","https://openalex.org/W1970859146","https://openalex.org/W1973610950","https://openalex.org/W1975347328","https://openalex.org/W1978394996","https://openalex.org/W1987777228","https://openalex.org/W1995247875","https://openalex.org/W2004455776","https://openalex.org/W2005207065","https://openalex.org/W2007395264","https://openalex.org/W2011265791","https://openalex.org/W2046967455","https://openalex.org/W2053549370","https://openalex.org/W2063198646","https://openalex.org/W2066636486","https://openalex.org/W2067223933","https://openalex.org/W2072840758","https://openalex.org/W2076008912","https://openalex.org/W2101005742","https://openalex.org/W2108346334","https://openalex.org/W2110224739","https://openalex.org/W2127674618","https://openalex.org/W2138621811","https://openalex.org/W2149684865","https://openalex.org/W2151626491","https://openalex.org/W2153635508","https://openalex.org/W2560674852","https://openalex.org/W2999905431","https://openalex.org/W3120421331","https://openalex.org/W4285719527","https://openalex.org/W6638689799"],"related_works":["https://openalex.org/W3115906952","https://openalex.org/W3134811395","https://openalex.org/W3155196058","https://openalex.org/W4252960523","https://openalex.org/W1529821365","https://openalex.org/W2135486207","https://openalex.org/W1499611046","https://openalex.org/W3024420453","https://openalex.org/W2083329789","https://openalex.org/W2376574812"],"abstract_inverted_index":{"It":[0],"is":[1,163],"well":[2],"known":[3],"that":[4,26,68,211],"links":[5,77],"are":[6,27,70,218],"an":[7],"important":[8],"source":[9],"of":[10,37,52,62,88,94,149,168,174],"information":[11],"when":[12],"dealing":[13],"with":[14,120,156],"Web":[15,31,57,100,118,183],"collections.":[16],"However,":[17,185],"the":[18,23,30,60,82,117,166,182,192,204,214],"question":[19],"remains":[20],"on":[21,29,108,132,165],"whether":[22],"same":[24],"techniques":[25],"used":[28],"can":[32],"be":[33],"applied":[34],"to":[35,111,123,176,201,224],"collections":[36],"documents":[38],"containing":[39],"citations":[40,55,75],"between":[41,74],"scientific":[42],"papers.":[43],"In":[44,102],"this":[45,79],"work":[46],"we":[47,84],"present":[48],"a":[49,86,91,99,138,144,151,157,196],"comparative":[50],"study":[51,198],"digital":[53,92,139,193],"library":[54,93],"and":[56,76,98,146,171],"links,":[58],"in":[59,71,78,116,137,178,181,191,219],"context":[61],"automatic":[63],"text":[64,126,153],"classification.":[65],"We":[66,141,209],"show":[67],"there":[69],"fact":[72,220],"differences":[73],"context.":[80],"For":[81],"comparison,":[83],"run":[85],"series":[87],"experiments":[89],"using":[90],"computer":[95],"science":[96],"papers":[97],"directory.":[101],"our":[103],"reference":[104],"collections,":[105],"measures":[106,130],"based":[107,127,131,154,159,164,216],"co-citation":[109],"tend":[110],"perform":[112,135],"better":[113,136],"for":[114,206,227],"pages":[115],"directory,":[119],"gains":[121,173],"up":[122,175],"37%":[124],"over":[125],"classifiers,":[128],"while":[129],"bibliographic":[133],"coupling":[134],"library.":[140,194],"also":[142],"propose":[143],"simple":[145],"effective":[147],"way":[148],"combining":[150],"traditional":[152],"classifier":[155,169],"citation-link":[158,215],"classifier.":[160],"This":[161],"combination":[162],"notion":[167],"reliability":[170],"presented":[172],"14%":[177],"micro-averaged":[179],"F1":[180],"collection.":[184],"no":[186],"significant":[187],"gain":[188],"was":[189,199],"obtained":[190],"Finally,":[195],"user":[197],"performed":[200],"further":[202],"investigate":[203],"causes":[205],"these":[207],"results.":[208],"discovered":[210],"misclassifications":[212],"by":[213],"classifiers":[217],"difficult":[221],"cases,":[222],"hard":[223],"classify":[225],"even":[226],"humans.":[228]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
