{"id":"https://openalex.org/W4393828048","doi":"https://doi.org/10.5281/zenodo.3254453","title":"Webis Open Directory Project Corpus 2010 (Webis-ODP-10)","display_name":"Webis Open Directory Project Corpus 2010 (Webis-ODP-10)","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W4393828048","doi":"https://doi.org/10.5281/zenodo.3254453"},"language":"en","primary_location":{"id":"pmh:oai:figshare.com:article/8318159","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026202614","display_name":"Dennis Hoppe","orcid":"https://orcid.org/0000-0001-8976-8603"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hoppe, Dennis","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stein, Benno","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"raw_orcid":"https://orcid.org/0000-0001-9033-2217","affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.1444000005722046,"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":0.1444000005722046,"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":0.07590000331401825,"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/T13629","display_name":"Text Readability and Simplification","score":0.058800000697374344,"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/directory","display_name":"Directory","score":0.9463852047920227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4351658225059509},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.41735705733299255},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4166693687438965},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3490365743637085},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34902793169021606},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1691586971282959},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08014726638793945}],"concepts":[{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.9463852047920227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4351658225059509},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.41735705733299255},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4166693687438965},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3490365743637085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34902793169021606},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1691586971282959},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08014726638793945},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:figshare.com:article/8318159","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"pmh:oai:zenodo.org:3254453","is_oa":true,"landing_page_url":"https://zenodo.org/record/3254453","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.3254453","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3254453","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/8318159","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","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/W2070622866"],"abstract_inverted_index":{"The":[0,18,45,101],"Webis":[1],"Open":[2,40,64],"Directory":[3,41,65],"Project":[4,42,66],"Corpus":[5],"2010":[6],"(Webis-ODP-10)":[7],"is":[8,78],"a":[9,172],"corpus":[10,19],"for":[11,107,113],"the":[12,37,57,63,87,118,135,164],"evaluation":[13],"of":[14,62,75,81,89,98,110,171,174],"cluster":[15],"labeling":[16],"algorithms.":[17],"contains":[20],"about":[21,126,130],"5,000":[22],"web":[23,46,124,137,146,153,169],"pages":[24,47,125,138,147,154,170],"which":[25,148],"are":[26,115,149],"grouped":[27],"into":[28],"4":[29,59],"main":[30],"categories":[31,61,77,102],"and":[32,72,159,182],"12":[33],"subcategories":[34,92],"based":[35],"on":[36],"human":[38],"made":[39],"(ODP)":[43],"classification.":[44],"were":[48,67,103,139,155,184],"collected":[49],"in":[50,163],"May":[51],"2010.":[52],"In":[53,86],"order":[54],"to":[55,83,94,105,116,122,161],"create":[56],"corpus,":[58],"different":[60,96,108],"chosen:":[68],"movies,":[69,90],"databases,":[70],"health":[71],"recreation.":[73],"Each":[74],"these":[76,91,152],"again":[79],"consists":[80],"up":[82],"six":[84,95],"subcategories.":[85],"case":[88],"correspond":[93],"titles":[97],"two":[99,119],"directors.":[100],"chosen":[104],"allow":[106],"settings":[109],"experiments.":[111],"Example":[112],"tasks":[114],"distinguish":[117],"directors":[120],"or":[121,176],"separate":[123],"recreation":[127],"from":[128,151],"those":[129],"health.":[131],"For":[132],"each":[133],"category,":[134],"linked":[136,150],"downloaded":[140,156],"if":[141],"they":[142],"still":[143],"existed.":[144],"Furthermore,":[145],"as":[157],"well":[158],"considered":[160],"be":[162],"same":[165],"category.":[166],"However,":[167],"only":[168],"length":[173],"1,000":[175],"more":[177],"characters":[178],"(excluding":[179],"HTML":[180],"tags":[181],"scripts)":[183],"kept.":[185]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
