{"id":"https://openalex.org/W2061022164","doi":"https://doi.org/10.1145/1451940.1451960","title":"A bottom-up approach for XML documents classification","display_name":"A bottom-up approach for XML documents classification","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2061022164","doi":"https://doi.org/10.1145/1451940.1451960","mag":"2061022164"},"language":"en","primary_location":{"id":"doi:10.1145/1451940.1451960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1451940.1451960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 international symposium on Database engineering & applications - IDEAS '08","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101431146","display_name":"Junwei Wu","orcid":"https://orcid.org/0009-0000-2297-3864"},"institutions":[{"id":"https://openalex.org/I130438778","display_name":"Memorial University of Newfoundland","ror":"https://ror.org/04haebc03","country_code":"CA","type":"education","lineage":["https://openalex.org/I130438778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Junwei Wu","raw_affiliation_strings":["Memorial University of Newfoundland , St. John\u2019s, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Memorial University of Newfoundland , St. John\u2019s, Canada","institution_ids":["https://openalex.org/I130438778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039176528","display_name":"Jian Tang","orcid":"https://orcid.org/0000-0003-4418-0114"},"institutions":[{"id":"https://openalex.org/I130438778","display_name":"Memorial University of Newfoundland","ror":"https://ror.org/04haebc03","country_code":"CA","type":"education","lineage":["https://openalex.org/I130438778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jian Tang","raw_affiliation_strings":["Memorial University of Newfoundland , St. John\u2019s, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Memorial University of Newfoundland , St. John\u2019s, Canada","institution_ids":["https://openalex.org/I130438778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130438778"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9979000091552734,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9947999715805054,"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":0.8785040378570557},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.7746360301971436},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7136039733886719},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6697956323623657},{"id":"https://openalex.org/keywords/sgml","display_name":"SGML","score":0.5580097436904907},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.5554632544517517},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.5542115569114685},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.5435937643051147},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.5341329574584961},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.5332192182540894},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.4926190972328186},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.43607857823371887},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28972405195236206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8785040378570557},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.7746360301971436},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7136039733886719},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6697956323623657},{"id":"https://openalex.org/C62701983","wikidata":"https://www.wikidata.org/wiki/Q207819","display_name":"SGML","level":4,"score":0.5580097436904907},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.5554632544517517},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.5542115569114685},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.5435937643051147},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.5341329574584961},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.5332192182540894},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.4926190972328186},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.43607857823371887},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28972405195236206}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1451940.1451960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1451940.1451960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 international symposium on Database engineering & applications - IDEAS '08","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W67881473","https://openalex.org/W1489432736","https://openalex.org/W1502851950","https://openalex.org/W1505155935","https://openalex.org/W1505796919","https://openalex.org/W1585743408","https://openalex.org/W1611570547","https://openalex.org/W1880452510","https://openalex.org/W2030766291","https://openalex.org/W2067223933","https://openalex.org/W2070046067","https://openalex.org/W2098508690","https://openalex.org/W2118020653","https://openalex.org/W2118965172","https://openalex.org/W2121715962","https://openalex.org/W2134222424","https://openalex.org/W2143774317","https://openalex.org/W2163360598","https://openalex.org/W2435251607","https://openalex.org/W2564184374"],"related_works":["https://openalex.org/W56340752","https://openalex.org/W4283736786","https://openalex.org/W2352672621","https://openalex.org/W2181356758","https://openalex.org/W1592776645","https://openalex.org/W2585052215","https://openalex.org/W3022924207","https://openalex.org/W2131299923","https://openalex.org/W1579700978","https://openalex.org/W1563174341"],"abstract_inverted_index":{"Extensible":[0],"Markup":[1],"Language":[2],"(XML)":[3],"is":[4,47,58,107,112,149],"a":[5,81,95,132,182],"simple":[6],"and":[7,122,142],"flexible":[8],"text":[9,140],"format":[10,50],"derived":[11],"from":[12,138,191],"SGML":[13],"[1].":[14],"It":[15],"has":[16],"been":[17],"widely":[18],"accepted":[19],"as":[20,33],"one":[21],"of":[22,40],"the":[23,41,88,117,123,139,145,152,162,169,172,186],"crucial":[24],"components":[25],"in":[26,155,171],"many":[27],"information":[28,165],"retrieval":[29],"related":[30],"applications,":[31],"such":[32],"XML":[34,85,156],"databases,":[35],"web":[36],"services,":[37],"etc.":[38],"One":[39],"reasons":[42],"for":[43,189],"its":[44,48,113],"wide":[45],"acceptance":[46],"customized":[49],"during":[51],"data":[52,55,61],"transmission":[53],"or":[54,100],"storage.":[56],"Classification":[57],"an":[59],"important":[60],"mining":[62],"task,":[63],"which":[64,72,98],"aims":[65],"to":[66,70,83,115],"assign":[67],"unknown":[68],"objects":[69],"classes":[71],"best":[73],"characterize":[74],"them.":[75],"In":[76],"this":[77,178],"paper,":[78],"we":[79,130,136],"propose":[80],"method":[82,106],"classify":[84],"documents":[86,157,190],"under":[87],"assumption":[89],"that":[90,154,177,193],"they":[91],"do":[92],"not":[93,102],"have":[94],"common":[96],"schema,":[97],"may":[99,101],"be":[103],"available.":[104],"Our":[105,174],"similarity-based.":[108],"Its":[109],"main":[110],"characteristics":[111],"way":[114],"handle":[116],"roles":[118],"played":[119],"by":[120,168],"texts":[121],"structural":[124,146],"information.":[125,147],"Unlike":[126],"most":[127,163],"existing":[128,187],"methods,":[129],"use":[131],"bottom-up":[133],"approach,":[134],"i.e.,":[135],"start":[137],"first,":[141],"then":[143],"embed":[144],"This":[148],"based":[150],"on":[151],"observation":[153],"with":[158],"diversified":[159],"tag":[160],"structures,":[161],"informative":[164],"are":[166],"carried":[167],"terms":[170],"texts.":[173],"experiments":[175],"show":[176],"strategy":[179],"can":[180],"achieve":[181],"better":[183],"performance":[184],"than":[185],"methods":[188],"sources":[192],"exhibit":[194],"heterogeneous":[195],"structures.":[196]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}