{"id":"https://openalex.org/W3107433986","doi":"https://doi.org/10.5281/zenodo.4064019","title":"Webis-Web-Archive-17","display_name":"Webis-Web-Archive-17","publication_year":2017,"publication_date":"2017-10-04","ids":{"openalex":"https://openalex.org/W3107433986","doi":"https://doi.org/10.5281/zenodo.4064019","mag":"3107433986"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.4064019","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4064019","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.4064019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037380544","display_name":"Johannes Kiesel","orcid":"https://orcid.org/0000-0002-1617-6508"},"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":true,"raw_author_name":"Kiesel, Johannes","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Potthast, Martin","raw_affiliation_strings":["Leipzig University"],"affiliations":[{"raw_affiliation_string":"Leipzig University","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014322854","display_name":"Matthias Hagen","orcid":"https://orcid.org/0000-0002-9733-2890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagen, Matthias","raw_affiliation_strings":["Halle University"],"affiliations":[{"raw_affiliation_string":"Halle University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014396215","display_name":"Florian Kneist","orcid":"https://orcid.org/0000-0002-4111-662X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kneist, Florian","raw_affiliation_strings":["Ulm University"],"affiliations":[{"raw_affiliation_string":"Ulm University","institution_ids":[]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037380544"],"corresponding_institution_ids":["https://openalex.org/I51441396"],"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/T12016","display_name":"Web Data Mining and Analysis","score":0.7896000146865845,"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":0.7896000146865845,"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/T13976","display_name":"Web visibility and informetrics","score":0.03240000084042549,"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/T11937","display_name":"Research Data Management Practices","score":0.02500000037252903,"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/world-wide-web","display_name":"World Wide Web","score":0.4976082146167755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4509914219379425},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3834426701068878}],"concepts":[{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4976082146167755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4509914219379425},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3834426701068878}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.4064019","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4064019","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.4064019","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4064019","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"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/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"The":[0,30],"Webis-Web-Archive-17":[1],"comprises":[2],"a":[3,22],"total":[4],"of":[5,24,41,50],"10,000":[6],"web":[7,28,34,43,52],"page":[8],"archives":[9],"from":[10,16],"mid-2017":[11],"that":[12,61],"were":[13],"carefully":[14],"sampled":[15],"the":[17,33],"Common":[18],"Crawl":[19],"to":[20],"involve":[21],"mixture":[23],"high-ranking":[25],"and":[26,39],"low-ranking":[27],"pages.":[29],"dataset":[31,70],"contains":[32],"archive":[35,53],"files,":[36],"HTML":[37],"DOM,":[38],"screenshots":[40],"each":[42],"page,":[44],"as":[45,47],"well":[46],"per-page":[48],"annotations":[49],"visual":[51],"quality.":[54],"See":[55],"this":[56,64,69,78],"overview":[57],"for":[58],"all":[59],"datasets":[60],"built":[62],"upon":[63],"one.":[65],"If":[66],"you":[67],"use":[68],"in":[71],"your":[72],"research,":[73],"please":[74],"cite":[75],"it":[76],"using":[77],"paper.":[79]},"counts_by_year":[],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}
