{"id":"https://openalex.org/W4324386260","doi":"https://doi.org/10.1007/s00799-023-00347-4","title":"CH-Bench: a user-oriented benchmark for systems for efficient distant reading (design, performance, and insights)","display_name":"CH-Bench: a user-oriented benchmark for systems for efficient distant reading (design, performance, and insights)","publication_year":2023,"publication_date":"2023-03-15","ids":{"openalex":"https://openalex.org/W4324386260","doi":"https://doi.org/10.1007/s00799-023-00347-4"},"language":"en","primary_location":{"id":"doi:10.1007/s00799-023-00347-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-023-00347-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-023-00347-4.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00799-023-00347-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033855019","display_name":"Jens Willkomm","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jens Willkomm","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031600781","display_name":"Markus Raster","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Raster","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033950182","display_name":"Martin Sch\u00e4ler","orcid":"https://orcid.org/0000-0003-1671-6508"},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Martin Sch\u00e4ler","raw_affiliation_strings":["University of Salzburg, Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"University of Salzburg, Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049768806","display_name":"Klemens B\u00f6hm","orcid":"https://orcid.org/0000-0002-1706-1913"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klemens B\u00f6hm","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033855019"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.1766,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52604622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"24","issue":"4","first_page":"243","last_page":"261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/T11719","display_name":"Data Quality and Management","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.9005841016769409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.861757755279541},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6623996496200562},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6242563724517822},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.5439959764480591},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4711422026157379},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4151148796081543},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35227033495903015}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.9005841016769409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.861757755279541},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6623996496200562},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6242563724517822},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5439959764480591},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4711422026157379},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4151148796081543},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35227033495903015},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00799-023-00347-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-023-00347-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-023-00347-4.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"},{"id":"pmh:oai:econstor.eu:10419/308618","is_oa":true,"landing_page_url":"https://hdl.handle.net/10419/308618","pdf_url":"https://www.econstor.eu/bitstream/10419/308618/1/s00799-023-00347-4.pdf","source":{"id":"https://openalex.org/S4306401696","display_name":"Econstor (Econstor)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:article"}],"best_oa_location":{"id":"doi:10.1007/s00799-023-00347-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-023-00347-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-023-00347-4.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4324386260.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W180578187","https://openalex.org/W1595443289","https://openalex.org/W1686065478","https://openalex.org/W1938298890","https://openalex.org/W2019096529","https://openalex.org/W2038411619","https://openalex.org/W2067481201","https://openalex.org/W2078924106","https://openalex.org/W2119984902","https://openalex.org/W2147152072","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2303924600","https://openalex.org/W2401667852","https://openalex.org/W2489913665","https://openalex.org/W2514454423","https://openalex.org/W2703465466","https://openalex.org/W2745338679","https://openalex.org/W2802416800","https://openalex.org/W2806668993","https://openalex.org/W2896457183","https://openalex.org/W2944989610","https://openalex.org/W2963099212","https://openalex.org/W2963780471","https://openalex.org/W3136510568","https://openalex.org/W4212800076","https://openalex.org/W4234918518","https://openalex.org/W4245561798","https://openalex.org/W4252352135","https://openalex.org/W4254304201","https://openalex.org/W6613547880","https://openalex.org/W6676070474"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Abstract":[0],"Data":[1],"science":[2],"deals":[3],"with":[4,118,160,186],"the":[5,20,32,56,59,85,119,134,140,147,161,177,195],"discovery":[6],"of":[7,12,36,55,61,84,133,142,149,164,179,197],"information":[8,131,162],"from":[9],"large":[10,23,64],"volumes":[11],"data.":[13],"The":[14],"data":[15,223],"studied":[16],"by":[17],"scientists":[18],"in":[19,158],"humanities":[21],"include":[22],"textual":[24],"corpora.":[25],"An":[26],"important":[27],"objective":[28],"is":[29,98,102],"to":[30,105,145,230],"study":[31],"ideas":[33],"and":[34,50,88,100,128,202,206,210],"expectations":[35,90],"a":[37,82,116,123],"society":[38,49],"regarding":[39,91,194],"specific":[40,150,214],"concepts,":[41],"like":[42],"\u201cfreedom\u201d":[43],"or":[44,213],"\u201cdemocracy,\u201d":[45],"both":[46],"for":[47,53,69,81],"today\u2019s":[48],"even":[51],"more":[52],"societies":[54],"past.":[57],"Studying":[58],"meaning":[60],"words":[62],"using":[63],"corpora":[65],"requires":[66],"efficient":[67,79],"systems":[68,78],"text":[70],"analysis,":[71],"so-called":[72],"distant":[73,107],"reading":[74,108],"systems.":[75,109],"Making":[76],"such":[77,115],"calls":[80],"specification":[83],"necessary":[86],"functionality":[87],"clear":[89],"typical":[92],"work":[93],"loads.":[94],"But":[95],"this":[96,111,153],"currently":[97],"unclear,":[99],"there":[101],"no":[103],"benchmark":[104,173,221],"evaluate":[106],"In":[110],"article,":[112],"we":[113,126,155,170,182,190,220],"propose":[114,171],"benchmark,":[117,181],"following":[120],"innovations:":[121],"As":[122],"first":[124],"step,":[125],"collect":[127],"structure":[129],"various":[130],"needs":[132,163],"target":[135],"users.":[136,165],"We":[137],"then":[138],"formalize":[139],"notion":[141],"word":[143],"context":[144],"facilitate":[146],"analysis":[148],"concepts.":[151],"Using":[152],"notion,":[154],"formulate":[156],"queries":[157],"line":[159],"Finally,":[166],"based":[167],"on":[168],"this,":[169],"concrete":[172],"queries.":[174],"To":[175],"demonstrate":[176],"benefit":[178],"our":[180],"conduct":[183],"an":[184],"evaluation,":[185],"two":[187],"objectives.":[188],"First,":[189],"aim":[191],"at":[192],"insights":[193],"content":[196],"different":[198,222],"corpora,":[199],"i.e.,":[200],"whether":[201],"how":[203],"their":[204],"size":[205],"nature":[207],"(e.g.,":[208],"popular":[209],"broad":[211],"literature":[212],"expert":[215],"literature)":[216],"affect":[217],"results.":[218],"Second,":[219],"management":[224],"technologies.":[225],"This":[226],"has":[227],"allowed":[228],"us":[229],"identify":[231],"performance":[232],"bottlenecks.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-16T09:10:04.655348","created_date":"2025-10-10T00:00:00"}
