{"id":"https://openalex.org/W2150112778","doi":"https://doi.org/10.1109/isspa.2010.5605508","title":"Mining Wikipedia Knowledge to improve document indexing and classification","display_name":"Mining Wikipedia Knowledge to improve document indexing and classification","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2150112778","doi":"https://doi.org/10.1109/isspa.2010.5605508","mag":"2150112778"},"language":"en","primary_location":{"id":"doi:10.1109/isspa.2010.5605508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2010.5605508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010)","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/A5081926578","display_name":"Ramesh Kumar Ayyasamy","orcid":"https://orcid.org/0000-0002-3538-3887"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ramesh Kumar Ayyasamy","raw_affiliation_strings":["School of IT, Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of IT, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041703685","display_name":"Bashar Tahayna","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bashar Tahayna","raw_affiliation_strings":["School of IT, Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of IT, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024500988","display_name":"Saadat M. Alhashmi","orcid":"https://orcid.org/0000-0003-4044-9315"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Saadat Alhashmi","raw_affiliation_strings":["School of IT, Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of IT, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075121844","display_name":"Eu-Gene Siew","orcid":"https://orcid.org/0000-0001-5725-4317"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Siew Eu-gene","raw_affiliation_strings":["School of IT, Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of IT, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054597061","display_name":"Simon Egerton","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Simon Egerton","raw_affiliation_strings":["School of IT, Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of IT, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1953,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94276753,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"806","last_page":"809"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9958000183105469,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8538525104522705},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.7889645099639893},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7353869080543518},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6449450254440308},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6403815746307373},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6277865171432495},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5498804450035095},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.42458558082580566},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4154578447341919},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3829778730869293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34499579668045044},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14952903985977173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8538525104522705},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.7889645099639893},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7353869080543518},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6449450254440308},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6403815746307373},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6277865171432495},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5498804450035095},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.42458558082580566},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4154578447341919},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3829778730869293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34499579668045044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14952903985977173},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isspa.2010.5605508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2010.5605508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W130742730","https://openalex.org/W167522204","https://openalex.org/W1487016832","https://openalex.org/W1595907733","https://openalex.org/W1711700449","https://openalex.org/W1996852448","https://openalex.org/W2027443251","https://openalex.org/W2065843886","https://openalex.org/W2071712180","https://openalex.org/W2100335205","https://openalex.org/W2108937378","https://openalex.org/W6605363618","https://openalex.org/W6606702763","https://openalex.org/W6629238926","https://openalex.org/W6674874269"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W3024364549","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W2573309543","https://openalex.org/W2805834743"],"abstract_inverted_index":{"Weblogs":[0],"are":[1,44],"an":[2],"important":[3],"source":[4],"of":[5,33,50,74,86,128],"information":[6],"that":[7,54,68,148],"requires":[8],"automatic":[9],"techniques":[10],"to":[11,17,89,98,104,112,117,131,150],"categorize":[12],"them":[13],"into":[14],"\u201ctopic-based\u201d":[15],"content,":[16],"facilitate":[18],"their":[19],"future":[20],"browsing":[21],"and":[22,29,71,76,156,161],"retrieval.":[23],"In":[24],"this":[25,80],"paper":[26],"we":[27],"propose":[28],"illustrate":[30],"the":[31,48,101,114,126,129,146,164],"effectiveness":[32],"a":[34,63,105,158],"new":[35],"tf.":[36],"idf":[37],"measure.":[38],"The":[39,57,94,122],"proposed":[40,83,142],"Conf.idf,":[41],"Catf.idf":[42],"measures":[43],"solely":[45],"based":[46],"on":[47],"mapping":[49],"terms-to-concepts-to-categories":[51],"(TCONCAT)":[52],"method":[53],"utilizes":[55],"Wikipedia.":[56],"Knowledge":[58],"base-Wikipedia":[59],"is":[60,97,125],"considered":[61],"as":[62,109,111],"large":[64],"scale":[65],"Web":[66],"encyclopaedia,":[67],"has":[69,157],"high-quality":[70],"huge":[72],"number":[73],"articles":[75],"categorical":[77],"indexes.":[78],"Using":[79],"system,":[81],"our":[82],"framework":[84],"consists":[85],"two":[87],"stages":[88],"solve":[90],"weblog":[91],"classification":[92],"problem.":[93],"first":[95],"stage":[96,124],"find":[99],"out":[100],"terms":[102,115],"belonging":[103,116],"unique":[106],"concept":[107],"(article),":[108],"well":[110],"disambiguate":[113],"more":[118,151],"than":[119,152,163],"one":[120,153],"concept.":[121],"second":[123],"determination":[127],"categories":[130],"which":[132],"these":[133],"found":[134],"concepts":[135],"belong":[136],"to.":[137],"Experimental":[138],"result":[139],"confirms":[140],"that,":[141],"system":[143],"can":[144],"distinguish":[145],"weblogs":[147],"belongs":[149],"category":[154],"efficiently":[155],"better":[159],"performance":[160],"success":[162],"traditional":[165],"statistical":[166],"Natural":[167],"Language":[168],"Processing-NLP":[169],"approaches.":[170]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
