{"id":"https://openalex.org/W2899042831","doi":"https://doi.org/10.1145/3239574","title":"Reproducible Web Corpora","display_name":"Reproducible Web Corpora","publication_year":2018,"publication_date":"2018-10-29","ids":{"openalex":"https://openalex.org/W2899042831","doi":"https://doi.org/10.1145/3239574","mag":"2899042831"},"language":"en","primary_location":{"id":"doi:10.1145/3239574","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3239574","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-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/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":"Johannes Kiesel","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"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":"Florian Kneist","raw_affiliation_strings":["Ulm University, Germany"],"affiliations":[{"raw_affiliation_string":"Ulm University, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025513989","display_name":"Milad Alshomary","orcid":"https://orcid.org/0000-0001-6142-9124"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Milad Alshomary","raw_affiliation_strings":["Paderborn University, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","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":"Benno Stein","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014322854","display_name":"Matthias Hagen","orcid":"https://orcid.org/0000-0002-9733-2890"},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Hagen","raw_affiliation_strings":["Martin-Luther-Universit\u00e4t Halle-Wittenberg, Germany"],"affiliations":[{"raw_affiliation_string":"Martin-Luther-Universit\u00e4t Halle-Wittenberg, Germany","institution_ids":["https://openalex.org/I68956291"]}]},{"author_position":"last","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":"Martin Potthast","raw_affiliation_strings":["Leipzig University, Germany"],"affiliations":[{"raw_affiliation_string":"Leipzig University, Germany","institution_ids":["https://openalex.org/I926574661"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037380544"],"corresponding_institution_ids":["https://openalex.org/I51441396"],"apc_list":null,"apc_paid":null,"fwci":4.3196,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95180461,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"10","issue":"4","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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/T11478","display_name":"Caching and Content Delivery","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/computer-science","display_name":"Computer science","score":0.8261665105819702},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7161918878555298},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.690139889717102},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.5200130939483643},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5096886157989502},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.4617348909378052},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.4613269865512848},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.4489341676235199},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.41954344511032104},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.416363000869751},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.328707218170166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261665105819702},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7161918878555298},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.690139889717102},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.5200130939483643},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5096886157989502},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.4617348909378052},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.4613269865512848},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.4489341676235199},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.41954344511032104},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.416363000869751},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.328707218170166}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3239574","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3239574","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W257652643","https://openalex.org/W1991286487","https://openalex.org/W2002796051","https://openalex.org/W2016053056","https://openalex.org/W2097942010","https://openalex.org/W2120101509","https://openalex.org/W2144206617","https://openalex.org/W2147800946","https://openalex.org/W2165718336","https://openalex.org/W2471939423","https://openalex.org/W2612649659","https://openalex.org/W2698462918","https://openalex.org/W2740290295","https://openalex.org/W2767512298","https://openalex.org/W2769066657"],"related_works":["https://openalex.org/W980488187","https://openalex.org/W2184421161","https://openalex.org/W2548494779","https://openalex.org/W2309621517","https://openalex.org/W1782470797","https://openalex.org/W1963685508","https://openalex.org/W2791261781","https://openalex.org/W2535301253","https://openalex.org/W68102627","https://openalex.org/W2116470944"],"abstract_inverted_index":{"The":[0,104,126],"evolution":[1],"of":[2,12,33,45,60,71,136,156,170,226,238],"web":[3,24,37,49,73,97,144,161,172,212,243],"pages":[4,8,38,173],"from":[5,143,176],"static":[6],"HTML":[7],"toward":[9],"dynamic":[10],"pieces":[11],"software":[13],"has":[14],"rendered":[15,160],"archiving":[16,215,234],"them":[17],"increasingly":[18],"difficult.":[19],"Nevertheless,":[20],"an":[21],"accurate,":[22],"reproducible":[23,72,129],"archive":[25,64],"is":[26,41],"a":[27,53,82,96,168],"necessity":[28],"to":[29,63,86,185,198,245],"ensure":[30],"the":[31,57,65,69,117,123,152,177,211,219,242],"reproducibility":[32],"web-based":[34],"research.":[35],"Archiving":[36],"reproducibly,":[39],"however,":[40],"currently":[42],"not":[43],"part":[44],"best":[46],"practices":[47],"for":[48,68,159,230],"corpus":[50,169],"construction.":[51],"As":[52],"result,":[54],"and":[55,134,180,216,235],"despite":[56],"ongoing":[58],"efforts":[59],"other":[61],"stakeholders":[62],"web,":[66],"tools":[67],"construction":[70],"corpora":[74],"are":[75,120],"insufficient":[76],"or":[77],"ill-fitted.":[78],"This":[79,223],"article":[80],"presents":[81],"new":[83],"tool":[84,127,240],"tailored":[85],"this":[87,192],"purpose.":[88],"It":[89],"relies":[90],"on":[91,111,140,191,207],"emulating":[92],"user":[93,106,130,132],"interactions":[94,107],"with":[95,122,183],"page":[98,119,213],"while":[99,113],"recording":[100],"all":[101],"network":[102],"traffic.":[103],"customizable":[105],"can":[108],"be":[109],"replayed":[110],"demand,":[112],"requests":[114],"sent":[115],"by":[116],"archived":[118],"served":[121],"recorded":[124],"responses.":[125],"facilitates":[128],"studies,":[131],"simulations,":[133],"evaluations":[135],"algorithms":[137],"that":[138],"rely":[139],"extracting":[141],"data":[142],"pages.":[145,162],"To":[146],"evaluate":[147],"our":[148,164,239],"tool,":[149,165],"we":[150,166,194],"conduct":[151],"first":[153],"systematic":[154],"assessment":[155,225],"reproduction":[157,186,227],"quality":[158,187,228],"Using":[163],"create":[167],"10,000":[171],"carefully":[174],"sampled":[175],"Common":[178],"Crawl":[179],"manually":[181],"annotated":[182],"regard":[184],"via":[188],"crowdsourcing.":[189],"Based":[190],"data,":[193],"test":[195],"three":[196],"approaches":[197],"automatic":[199,224],"reproduction-quality":[200],"assessment.":[201],"An":[202],"off-the-shelf":[203],"neural":[204],"network,":[205],"trained":[206],"visual":[208],"differences":[209],"between":[210],"during":[214,233],"reproduction,":[217],"matches":[218],"manual":[220],"assessments":[221],"best.":[222],"allows":[229],"immediate":[231],"bugfixing":[232],"continuous":[236],"development":[237],"as":[241],"continues":[244],"evolve.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
