{"id":"https://openalex.org/W2115155123","doi":"https://doi.org/10.1145/1135777.1135991","title":"Towards practical genre classification of web documents","display_name":"Towards practical genre classification of web documents","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2115155123","doi":"https://doi.org/10.1145/1135777.1135991","mag":"2115155123"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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/A5049193888","display_name":"George Ferizis","orcid":null},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"George Ferizis","raw_affiliation_strings":["CSIRO ICT Centre, ANU Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO ICT Centre, ANU Canberra, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017503948","display_name":"Peter Bailey","orcid":null},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter Bailey","raw_affiliation_strings":["CSIRO ICT Centre, ANU Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO ICT Centre, ANU Canberra, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049193888"],"corresponding_institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"],"apc_list":null,"apc_paid":null,"fwci":2.326,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89571948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1013","last_page":"1014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9997000098228455,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9847000241279602,"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/term","display_name":"Term (time)","score":0.8192610144615173},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.787377119064331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.745539128780365},{"id":"https://openalex.org/keywords/linguistic-analysis","display_name":"Linguistic analysis","score":0.6225835084915161},{"id":"https://openalex.org/keywords/frequency-analysis","display_name":"Frequency analysis","score":0.5411043167114258},{"id":"https://openalex.org/keywords/frequency","display_name":"Frequency","score":0.5103201270103455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4720015525817871},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4708539843559265},{"id":"https://openalex.org/keywords/genre-analysis","display_name":"Genre analysis","score":0.4296422600746155},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3720107078552246},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3179364800453186},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2753024697303772},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15386885404586792},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13506942987442017}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.8192610144615173},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.787377119064331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745539128780365},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.6225835084915161},{"id":"https://openalex.org/C97118885","wikidata":"https://www.wikidata.org/wiki/Q565636","display_name":"Frequency analysis","level":2,"score":0.5411043167114258},{"id":"https://openalex.org/C199075045","wikidata":"https://www.wikidata.org/wiki/Q762856","display_name":"Frequency","level":2,"score":0.5103201270103455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4720015525817871},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4708539843559265},{"id":"https://openalex.org/C2983877603","wikidata":"https://www.wikidata.org/wiki/Q5533546","display_name":"Genre analysis","level":2,"score":0.4296422600746155},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3720107078552246},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3179364800453186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2753024697303772},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15386885404586792},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13506942987442017},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1135777.1135991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.5775","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.5775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://es.csiro.au/pubs/ferizis_genre.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1968855371","https://openalex.org/W2038201841","https://openalex.org/W2081687495","https://openalex.org/W2146888100","https://openalex.org/W2165431734","https://openalex.org/W2949696181"],"related_works":["https://openalex.org/W3157343726","https://openalex.org/W1020241430","https://openalex.org/W2964301755","https://openalex.org/W2053987674","https://openalex.org/W2713137291","https://openalex.org/W2004247964","https://openalex.org/W3169996680","https://openalex.org/W2346734981","https://openalex.org/W3121853264","https://openalex.org/W2115155123"],"abstract_inverted_index":{"Classification":[0],"of":[1,30,33,70,79,106,109,125],"documents":[2],"by":[3],"genre":[4],"is":[5,73,121],"typically":[6],"done":[7],"either":[8],"using":[9],"linguistic":[10,48,71,86,110],"analysis":[11,41,72,87,111],"or":[12,65],"term":[13,39,89,113,126],"frequency":[14,40,90,114,127],"based":[15],"techniques.":[16],"The":[17,92],"former":[18],"provides":[19],"better":[20],"classification":[21,52],"accuracy":[22,53,75,119],"than":[23,47,123],"the":[24,28,55,67,104],"latter":[25],"but":[26],"at":[27],"cost":[29],"two":[31],"orders":[32],"magnitude":[34],"more":[35],"computation":[36,77,105],"time.":[37],"While":[38],"requires":[42],"much":[43],"less":[44],"computational":[45],"resources":[46],"analysis,it":[49],"returns":[50],"poor":[51],"when":[54],"genres":[56],"are":[57],"not":[58],"sufficiently":[59],"distinct.":[60],"A":[61],"method":[62,81,100],"that":[63,98,120,124],"removes":[64],"approximates":[66],"expensive":[68],"portions":[69],"presented.The":[74],"and":[76,88,112],"time":[78,108],"this":[80,95,99],"then":[82],"compared":[83],"with":[84],"both":[85,107],"analysis.":[91,128],"results":[93],"in":[94],"paper":[96],"show":[97],"can":[101],"significantly":[102],"reduce":[103],"analysis,":[115],"while":[116],"retaining":[117],"an":[118],"higher":[122]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
