{"id":"https://openalex.org/W4288073756","doi":"https://doi.org/10.18420/inf2020_05","title":"28. September - 2. Oktober 2020","display_name":"28. September - 2. Oktober 2020","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W4288073756","doi":"https://doi.org/10.18420/inf2020_05"},"language":"en","primary_location":{"id":"doi:10.18420/inf2020_05","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2020_05","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article-journal"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/inf2020_05","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037682495","display_name":"Michael V\u00f6lske","orcid":"https://orcid.org/0000-0002-9283-6846"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"V\u00f6lske, Michael","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079524270","display_name":"Janek Bevendorff","orcid":"https://orcid.org/0000-0002-3797-0559"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bevendorff, Janek","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037380544","display_name":"Johannes Kiesel","orcid":"https://orcid.org/0000-0002-1617-6508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiesel, Johannes","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stein, Benno","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068616222","display_name":"Maik Fr\u00f6be","orcid":"https://orcid.org/0000-0002-1003-981X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fr\u00f6be, Maik","raw_affiliation_strings":[],"affiliations":[]},{"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":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Potthast, Martin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5037682495"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38422988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9941999912261963,"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":0.9941999912261963,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9412999749183655,"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/world-wide-web","display_name":"World Wide Web","score":0.7933356165885925},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.7342941164970398},{"id":"https://openalex.org/keywords/treasure","display_name":"Treasure","score":0.6393515467643738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6363760232925415},{"id":"https://openalex.org/keywords/web-analytics","display_name":"Web analytics","score":0.5746591091156006},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5493653416633606},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5412096977233887},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.507183313369751},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4570803940296173},{"id":"https://openalex.org/keywords/internet-research","display_name":"Internet research","score":0.4406476616859436},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.438678115606308},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.4254250228404999},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.4116085171699524},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.3411768078804016},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.283316433429718},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11210623383522034},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1009669303894043}],"concepts":[{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7933356165885925},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.7342941164970398},{"id":"https://openalex.org/C2776084483","wikidata":"https://www.wikidata.org/wiki/Q272937","display_name":"Treasure","level":2,"score":0.6393515467643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363760232925415},{"id":"https://openalex.org/C516187249","wikidata":"https://www.wikidata.org/wiki/Q10719477","display_name":"Web analytics","level":5,"score":0.5746591091156006},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5493653416633606},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5412096977233887},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.507183313369751},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4570803940296173},{"id":"https://openalex.org/C134531850","wikidata":"https://www.wikidata.org/wiki/Q6056040","display_name":"Internet research","level":3,"score":0.4406476616859436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.438678115606308},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.4254250228404999},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.4116085171699524},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.3411768078804016},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.283316433429718},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11210623383522034},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1009669303894043},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/inf2020_05","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2020_05","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/inf2020_05","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2020_05","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article-journal"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3174726539","https://openalex.org/W2182629206","https://openalex.org/W2622968908","https://openalex.org/W2360015638","https://openalex.org/W1861234877","https://openalex.org/W1523783981","https://openalex.org/W3139873369","https://openalex.org/W2546858440","https://openalex.org/W2954487097","https://openalex.org/W141438787"],"abstract_inverted_index":{"Web":[0],"archive":[1,108,137,166],"analytics":[2],"is":[3,71],"the":[4,17,28,33,40,43,62,75,79,90,97,116,140,147,162,168],"exploitation":[5],"of":[6,30,36,42,85,105,115,135,149,161],"publicly":[7],"accessible":[8],"web":[9,67,107,136,154,165],"pages":[10],"and":[11,47,65,143,156],"their":[12],"evolution":[13],"for":[14,21,109,123],"research":[15,81,110],"purposes\u2014to":[16],"extent":[18],"organizationally":[19],"possible":[20],"researchers.":[22],"In":[23],"order":[24],"to":[25,55,88,100],"better":[26],"understand":[27],"complexity":[29],"this":[31,37,125],"task,":[32],"first":[34],"part":[35,104,114],"paper":[38,117],"puts":[39],"entirety":[41],"world's":[44],"captured,":[45],"created,":[46],"replicated":[48],"data":[49,58,126,138],"(the":[50],"\u201cGlobal":[51],"Datasphere\u201d)":[52],"in":[53,118],"relation":[54],"other":[56],"important":[57],"sets":[59],"such":[60],"as":[61],"public":[63],"internet":[64],"its":[66,106],"pages,":[68],"or":[69],"what":[70],"preserved":[72],"thereof":[73],"by":[74],"Internet":[76,98,141,169],"Archive.":[77,170],"Recently,":[78],"Webis":[80],"group,":[82],"a":[83,102,158],"network":[84],"university":[86],"chairs":[87],"which":[89],"authors":[91],"belong,":[92],"concluded":[93],"an":[94],"agreement":[95],"with":[96,146],"Archive":[99,142],"download":[101],"substantial":[103],"purposes.":[111],"The":[112],"second":[113],"hand":[119],"describes":[120],"our":[121],"infrastructure":[122],"processing":[124],"treasure:":[127],"We":[128],"will":[129],"eventually":[130],"host":[131],"around":[132],"8":[133],"PB":[134,164],"from":[139],"Common":[144],"Crawl,":[145],"goal":[148],"supplementing":[150],"existing":[151],"large":[152],"scale":[153],"corpora":[155],"forming":[157],"non-biased":[159],"subset":[160],"30":[163],"at":[167]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2022-07-28T00:00:00"}
