{"id":"https://openalex.org/W2514443376","doi":"https://doi.org/10.18653/v1/w16-2611","title":"Genre classification for a corpus of academic webpages","display_name":"Genre classification for a corpus of academic webpages","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2514443376","doi":"https://doi.org/10.18653/v1/w16-2611","mag":"2514443376"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2611","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2611","pdf_url":"https://www.aclweb.org/anthology/W16-2611.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Web as Corpus Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2611.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008071406","display_name":"Erika Dalan","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Erika Dalan","raw_affiliation_strings":["University of Bologna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072701587","display_name":"Serge Sharoff","orcid":"https://orcid.org/0000-0002-4877-0210"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Serge Sharoff","raw_affiliation_strings":["University of Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.05428064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"90","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9919999837875366,"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/T10759","display_name":"Translation Studies and Practices","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6801595687866211},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6087903380393982},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5552807450294495},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5216872692108154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48740154504776},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3750153183937073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6801595687866211},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6087903380393982},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5552807450294495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5216872692108154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48740154504776},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3750153183937073}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w16-2611","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2611","pdf_url":"https://www.aclweb.org/anthology/W16-2611.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Web as Corpus Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/597734","is_oa":false,"landing_page_url":"http://hdl.handle.net/11585/597734","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2611","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2611","pdf_url":"https://www.aclweb.org/anthology/W16-2611.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Web as Corpus Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2514443376.pdf","grobid_xml":"https://content.openalex.org/works/W2514443376.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W40340171","https://openalex.org/W1519635394","https://openalex.org/W1607330352","https://openalex.org/W1607545660","https://openalex.org/W1826705282","https://openalex.org/W1964357740","https://openalex.org/W2006943109","https://openalex.org/W2107425660","https://openalex.org/W2114097960","https://openalex.org/W2125528933","https://openalex.org/W2134943861","https://openalex.org/W2137579698","https://openalex.org/W2151560261","https://openalex.org/W2153547334","https://openalex.org/W2187428037","https://openalex.org/W2582107614","https://openalex.org/W2728215186","https://openalex.org/W2964153337","https://openalex.org/W3165616014","https://openalex.org/W3205853728","https://openalex.org/W4285719527","https://openalex.org/W4298867617"],"related_works":["https://openalex.org/W1488511360","https://openalex.org/W3204019825","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2106946048","https://openalex.org/W2000745862","https://openalex.org/W2120930843"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,56],"report":[4],"our":[5],"analysis":[6],"of":[7,21,26,53,60,72,79,83,111,121],"the":[8,27,45,70,73,87,91,109,118],"similarities":[9],"between":[10],"webpages":[11],"that":[12,63],"are":[13,99],"crawled":[14],"from":[15],"European":[16],"academic":[17,84],"websites,":[18],"and":[19,39,107,128],"comparison":[20],"their":[22,40,66],"distribution":[23,110],"in":[24,102],"terms":[25],"English":[28,32,34,126],"language":[29,41,123,129],"variety":[30],"(native":[31],"vs":[33],"as":[35],"a":[36,51,58,80],"lingua":[37],"franca)":[38],"family":[42],"(based":[43],"on":[44,94],"country's":[46],"official":[47],"language).":[48],"After":[49],"building":[50],"corpus":[52],"university":[54],"webpages,":[55],"selected":[57],"set":[59],"relevant":[61],"descriptors":[62],"can":[64],"represent":[65],"text":[67,112],"types":[68,113],"using":[69],"framework":[71],"Functional":[74],"Text":[75],"Dimensions.":[76],"Manual":[77],"annotation":[78],"random":[81],"sample":[82],"pages":[85],"provides":[86],"basis":[88],"for":[89],"classifying":[90],"remaining":[92],"texts":[93],"each":[95,115],"dimension.":[96],"Reliable":[97],"thresholds":[98],"then":[100],"determined":[101],"order":[103],"to":[104],"evaluate":[105],"precision":[106],"assess":[108],"by":[114],"dimension,":[116],"with":[117],"ultimate":[119],"goal":[120],"analysing":[122],"features":[124],"over":[125],"varieties":[127],"families.":[130]},"counts_by_year":[{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
