{"id":"https://openalex.org/W2083089853","doi":"https://doi.org/10.1145/2380718.2380762","title":"The evolution of a crawling strategy for an academic document search engine","display_name":"The evolution of a crawling strategy for an academic document search engine","publication_year":2012,"publication_date":"2012-06-22","ids":{"openalex":"https://openalex.org/W2083089853","doi":"https://doi.org/10.1145/2380718.2380762","mag":"2083089853"},"language":"en","primary_location":{"id":"doi:10.1145/2380718.2380762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2380718.2380762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th Annual ACM Web Science Conference","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/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Pennsylvania State University, PA","[Pennsylvania State University, PA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"[Pennsylvania State University, PA]","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026411226","display_name":"Pradeep B. Teregowda","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pradeep Teregowda","raw_affiliation_strings":["Pennsylvania State University, PA","[Pennsylvania State University, PA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"[Pennsylvania State University, PA]","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026314030","display_name":"Juan Pablo Fern\u00e1ndez Ram\u00edrez","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Fern\u00e1ndez Ram\u00edrez","raw_affiliation_strings":["Pennsylvania State University, PA","[Pennsylvania State University, PA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"[Pennsylvania State University, PA]","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasenjit Mitra","raw_affiliation_strings":["Pennsylvania State University, PA","[Pennsylvania State University, PA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"[Pennsylvania State University, PA]","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078436441","display_name":"Shuyi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuyi Zheng","raw_affiliation_strings":["Facebook Inc., Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc., Menlo Park, CA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Pennsylvania State University, PA","[Pennsylvania State University, PA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"[Pennsylvania State University, PA]","institution_ids":["https://openalex.org/I130769515"]}]}],"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":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"340","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9824000000953674,"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/T11478","display_name":"Caching and Content Delivery","score":0.9646999835968018,"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/blacklist","display_name":"Blacklist","score":0.8733618259429932},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8605755567550659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7293880581855774},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7267783880233765},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7037216424942017},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5820568203926086},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5799527168273926},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.4519375264644623},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4337875247001648},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4297619163990021},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4245813488960266},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.2889097034931183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10080698132514954},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.07832536101341248}],"concepts":[{"id":"https://openalex.org/C2781345505","wikidata":"https://www.wikidata.org/wiki/Q2535979","display_name":"Blacklist","level":2,"score":0.8733618259429932},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8605755567550659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293880581855774},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7267783880233765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7037216424942017},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5820568203926086},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5799527168273926},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.4519375264644623},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4337875247001648},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4297619163990021},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4245813488960266},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2889097034931183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10080698132514954},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.07832536101341248},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2380718.2380762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2380718.2380762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th Annual ACM Web Science Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332186","display_name":"Defense Threat Reduction Agency","ror":"https://ror.org/04tz64554"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W14315322","https://openalex.org/W182781187","https://openalex.org/W2029341294","https://openalex.org/W2055950890","https://openalex.org/W2097704339","https://openalex.org/W2911388033","https://openalex.org/W6607445943"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W4248730791","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W2372594123"],"abstract_inverted_index":{"We":[0,149,182],"present":[1],"a":[2,9,61,75,78,98,195],"preliminary":[3],"study":[4],"of":[5,8,101,133,198],"the":[6,24,82,93,141,145,151,186,190],"evolution":[7],"crawling":[10,83,185],"strategy":[11],"for":[12,26,154],"an":[13],"academic":[14,27],"document":[15,162],"search":[16,65],"engine,":[17],"in":[18,32,70,144],"particular":[19],"CiteSeerX.":[20],"CiteSeerX":[21,57,142],"actively":[22],"crawls":[23],"web":[25],"and":[28,34,37,43,53,80,86,119,164,201],"research":[29],"documents":[30],"primarily":[31],"computer":[33],"information":[35,41,46],"sciences,":[36],"then":[38,170],"performs":[39],"unique":[40],"extraction":[42],"indexing":[44],"extracting":[45],"such":[47,56,103],"as":[48,104],"OAI":[49],"metadata,":[50],"citations,":[51],"tables":[52],"others.":[54],"As":[55],"could":[58],"be":[59],"considered":[60,118],"specialty":[62],"or":[63],"vertical":[64],"engine.":[66],"To":[67],"improve":[68],"precision":[69,192],"resources":[71],"expended,":[72],"we":[73],"replace":[74],"blacklist":[76,91],"with":[77],"whitelist":[79,112,125,168,187],"compare":[81],"efficiencies":[84],"before":[85],"after":[87],"this":[88],"change.":[89],"A":[90,111],"means":[92,113],"crawl":[94,191],"is":[95,108,126,169],"forbidden":[96],"from":[97],"certain":[99,115],"list":[100],"URLs":[102,138,175],"publisher":[105],"domains":[106,116],"but":[107],"otherwise":[109],"unlimited.":[110],"only":[114],"are":[117,121],"others":[120],"not":[122],"crawled":[123],"The":[124,167],"generated":[127,171],"based":[128,176],"on":[129,177],"domain":[130,156,179],"ranking":[131,180],"scores":[132,153],"approximately":[134],"five":[135],"million":[136],"parent":[137,174],"harvested":[139],"by":[140,157,172,193],"crawler":[143],"past":[146],"four":[147],"years.":[148],"calculate":[150],"F1":[152],"each":[155],"applying":[158],"equal":[159],"weights":[160],"to":[161],"numbers":[163],"citation":[165],"rates.":[166],"re-ordering":[173],"their":[178],"scores.":[181],"found":[183],"that":[184],"significantly":[188],"increases":[189],"reducing":[194],"large":[196],"amount":[197],"irrelevant":[199],"requests":[200],"downloads.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
