{"id":"https://openalex.org/W90672828","doi":"https://doi.org/10.1145/2567948.2579045","title":"Infrastructure for supporting exploration and discovery in web archives","display_name":"Infrastructure for supporting exploration and discovery in web archives","publication_year":2014,"publication_date":"2014-04-07","ids":{"openalex":"https://openalex.org/W90672828","doi":"https://doi.org/10.1145/2567948.2579045","mag":"90672828"},"language":"en","primary_location":{"id":"doi:10.1145/2567948.2579045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567948.2579045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on World Wide Web","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046761326","display_name":"Milad Gholami","orcid":"https://orcid.org/0000-0002-7201-8301"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milad Gholami","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075728689","display_name":"Jinfeng Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinfeng Rao","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":3.7221,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93716023,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"851","last_page":"856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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":0.9990000128746033,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976999759674072,"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/T11478","display_name":"Caching and Content Delivery","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8257143497467041},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7164947390556335},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.688068151473999},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6351691484451294},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5306405425071716},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.442121297121048},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.43955376744270325},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43361207842826843},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.31030625104904175},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09670549631118774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257143497467041},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7164947390556335},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.688068151473999},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6351691484451294},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5306405425071716},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.442121297121048},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.43955376744270325},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43361207842826843},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.31030625104904175},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09670549631118774}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2567948.2579045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567948.2579045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.698.5434","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.698.5434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://cs.uwaterloo.ca/%7Ejimmylin/publications/Lin_etal_TempWeb2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6164524237","display_name":null,"funder_award_id":"IIS-1144034 and IIS-1218043","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W51109661","https://openalex.org/W130255415","https://openalex.org/W192446467","https://openalex.org/W195590691","https://openalex.org/W1483194439","https://openalex.org/W1540236587","https://openalex.org/W1551737895","https://openalex.org/W1880262756","https://openalex.org/W1964338930","https://openalex.org/W1981420413","https://openalex.org/W1985125789","https://openalex.org/W2022507549","https://openalex.org/W2090491854","https://openalex.org/W2097411811","https://openalex.org/W2098935637","https://openalex.org/W2126399065","https://openalex.org/W2131975293","https://openalex.org/W2157748587","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2400669547","https://openalex.org/W2624304035"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248"],"abstract_inverted_index":{"Web":[0],"archiving":[1],"initiatives":[2],"around":[3],"the":[4,18,69,112],"world":[5],"capture":[6],"ephemeral":[7],"web":[8,21,65],"content":[9,85],"to":[10,36,42,138],"preserve":[11],"our":[12],"collective":[13],"digital":[14],"memory.":[15],"However,":[16],"unlocking":[17],"potential":[19],"of":[20,30,114],"archives":[22,66],"requires":[23],"tools":[24,34,99],"that":[25,47,123,135],"support":[26],"exploration":[27],"and":[28,39,41,82,90,102,116,127],"discovery":[29],"captured":[31],"content.":[32,141],"These":[33],"need":[35],"be":[37],"scalable":[38,115],"responsive,":[40],"this":[43],"end":[44],"we":[45],"believe":[46],"modern":[48],"\"big":[49],"data\"":[50],"infrastructure":[51,110],"can":[52],"provide":[53],"a":[54,76,121],"solid":[55],"foundation.":[56],"We":[57,119],"present":[58],"Warcbase,":[59],"an":[60,128],"open-source":[61],"platform":[62],"for":[63,80,100,108],"managing":[64,83],"built":[67],"on":[68,106,132],"distributed":[70],"datastore":[71],"HBase.":[72],"Our":[73],"system":[74],"provides":[75,97,124],"flexible":[77],"data":[78,103],"model":[79],"storing":[81],"raw":[84],"as":[86,88],"well":[87],"metadata":[89],"extracted":[91],"knowledge.":[92],"Tight":[93],"integration":[94],"with":[95],"Hadoop":[96],"powerful":[98],"analytics":[101],"processing.":[104],"Relying":[105],"HBase":[107],"storage":[109],"simplifies":[111],"development":[113],"responsive":[117],"applications.":[118],"describe":[120],"service":[122],"temporal":[125],"browsing":[126],"interactive":[129],"visualization":[130],"based":[131],"topic":[133],"models":[134],"allows":[136],"users":[137],"explore":[139],"archived":[140]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
