{"id":"https://openalex.org/W3046234757","doi":"https://doi.org/10.1145/3383583.3398540","title":"Identifying Documents In-Scope of a Collection from Web Archives","display_name":"Identifying Documents In-Scope of a Collection from Web Archives","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3046234757","doi":"https://doi.org/10.1145/3383583.3398540","mag":"3046234757"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398540","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383583.3398540","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383583.3398540","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3383583.3398540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Krutarth Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krutarth Patel","raw_affiliation_strings":["Kansas State University, Manhattan, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cornelia Caragea","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mark E. Phillips","orcid":null},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark E. Phillips","raw_affiliation_strings":["University of North Texas, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas, New York, NY, USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":null,"display_name":"Nathaniel T. Fox","orcid":null},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel T. Fox","raw_affiliation_strings":["University of North Texas, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas, New York, NY, USA","institution_ids":["https://openalex.org/I123534392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"176"},"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9936000108718872,"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/focus","display_name":"Focus (optics)","score":0.6328999996185303},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.44020000100135803},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41499999165534973},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.3686999976634979},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.3377000093460083},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.30550000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687000036239624},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.652899980545044},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6328999996185303},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6079000234603882},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.44020000100135803},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.3377000093460083},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3383583.3398540","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383583.3398540","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383583.3398540","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.00611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.00611","pdf_url":"https://arxiv.org/pdf/2009.00611","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3383583.3398540","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383583.3398540","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383583.3398540","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8637092633","display_name":null,"funder_award_id":"LG-71-17-0202-17","funder_id":"https://openalex.org/F4320306122","funder_display_name":"Institute of Museum and Library Services"}],"funders":[{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3046234757.pdf","grobid_xml":"https://content.openalex.org/works/W3046234757.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2117130368","https://openalex.org/W2118020653","https://openalex.org/W2133173492","https://openalex.org/W2141763599","https://openalex.org/W2464674082","https://openalex.org/W2735186627","https://openalex.org/W2820220568","https://openalex.org/W2911964244","https://openalex.org/W2968217254","https://openalex.org/W2997617958","https://openalex.org/W3005526988","https://openalex.org/W3006210356"],"related_works":[],"abstract_inverted_index":{"Web":[0,139],"archive":[1],"data":[2],"usually":[3],"contains":[4],"high-quality":[5],"documents":[6,41,53,79,157],"that":[7,37,120,133,145,149],"are":[8],"very":[9],"useful":[10],"for":[11,34,44,76],"creating":[12],"specialized":[13],"collections":[14],"of":[15,23,42,48,52,80,99,112,124,155],"documents,":[16],"e.g.,":[17],"scientific":[18],"digital":[19],"libraries":[20],"and":[21,67,93,97],"repositories":[22],"technical":[24],"reports.":[25],"In":[26,59],"doing":[27],"so,":[28],"there":[29],"is":[30],"a":[31,45],"substantial":[32],"need":[33],"automatic":[35],"approaches":[36],"can":[38],"distinguish":[39],"the":[40,49,72,78,83,105,113,122,146,156,160],"interest":[43,81],"collection":[46],"out":[47],"huge":[50],"number":[51],"collected":[54],"by":[55],"web":[56,84],"archiving":[57],"institutions.":[58],"this":[60],"paper,":[61],"we":[62,88,134],"explore":[63],"different":[64,138],"learning":[65,92,95],"models":[66,96],"feature":[68],"representations":[69],"to":[70],"determine":[71],"best":[73],"performing":[74],"ones":[75],"identifying":[77],"from":[82,104,109,136],"archived":[85],"data.":[86],"Specifically,":[87],"study":[89],"both":[90],"machine":[91],"deep":[94],"\"bag":[98],"words\"":[100],"(BoW)":[101],"features":[102,119],"extracted":[103],"entire":[106],"document":[107],"or":[108],"specific":[110,153],"portions":[111,154],"document,":[114],"as":[115,117],"well":[116],"structural":[118],"capture":[121],"structure":[123],"documents.":[125],"We":[126],"focus":[127,150],"our":[128],"evaluation":[129],"on":[130,152,167],"three":[131,137,169],"datasets":[132],"created":[135],"archives.":[140],"Our":[141],"experimental":[142],"results":[143],"show":[144],"BoW":[147],"classifiers":[148],"only":[151],"(rather":[158],"than":[159],"full":[161],"text)":[162],"outperform":[163],"all":[164,168],"compared":[165],"methods":[166],"datasets.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-08-07T00:00:00"}
