{"id":"https://openalex.org/W2103224511","doi":"https://doi.org/10.1145/1142473.1142504","title":"To search or to crawl?","display_name":"To search or to crawl?","publication_year":2006,"publication_date":"2006-06-27","ids":{"openalex":"https://openalex.org/W2103224511","doi":"https://doi.org/10.1145/1142473.1142504","mag":"2103224511"},"language":"en","primary_location":{"id":"doi:10.1145/1142473.1142504","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1142473.1142504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-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/A5010731709","display_name":"Panagiotis G. Ipeirotis","orcid":"https://orcid.org/0000-0002-2966-7402"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Panagiotis G. Ipeirotis","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028578280","display_name":"Eugene Agichtein","orcid":"https://orcid.org/0000-0002-3148-5448"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Eugene Agichtein","raw_affiliation_strings":["Microsoft Research","Microsoft research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048728819","display_name":"Pranay Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranay Jain","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080063580","display_name":"Luis Gravano","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Gravano","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010731709"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":31.2023,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.99585267,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"265","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9955999851226807,"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/T10260","display_name":"Software Engineering Research","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8834978342056274},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6820025444030762},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5412490367889404},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.5340840816497803},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5118183493614197},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.4886801540851593},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4831635355949402},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34773844480514526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3422406315803528},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3237902820110321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8834978342056274},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6820025444030762},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5412490367889404},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.5340840816497803},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5118183493614197},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.4886801540851593},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4831635355949402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34773844480514526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3422406315803528},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3237902820110321},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1142473.1142504","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1142473.1142504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W108157922","https://openalex.org/W109105922","https://openalex.org/W1489949474","https://openalex.org/W1489992655","https://openalex.org/W1517178556","https://openalex.org/W1520232900","https://openalex.org/W1570968730","https://openalex.org/W1586176254","https://openalex.org/W1587932711","https://openalex.org/W1943309769","https://openalex.org/W1986828474","https://openalex.org/W2016892599","https://openalex.org/W2017726337","https://openalex.org/W2026080185","https://openalex.org/W2075261997","https://openalex.org/W2079656678","https://openalex.org/W2079806729","https://openalex.org/W2081948558","https://openalex.org/W2084134149","https://openalex.org/W2084812512","https://openalex.org/W2086253379","https://openalex.org/W2094930182","https://openalex.org/W2096891167","https://openalex.org/W2103931177","https://openalex.org/W2105423800","https://openalex.org/W2105995744","https://openalex.org/W2112976607","https://openalex.org/W2115461474","https://openalex.org/W2116341550","https://openalex.org/W2118020653","https://openalex.org/W2118229812","https://openalex.org/W2124673015","https://openalex.org/W2125969310","https://openalex.org/W2131006463","https://openalex.org/W2137845970","https://openalex.org/W2140796896","https://openalex.org/W2148603752","https://openalex.org/W2151007976","https://openalex.org/W2152766222","https://openalex.org/W2154148563","https://openalex.org/W2158011814","https://openalex.org/W2169015768","https://openalex.org/W2322524800","https://openalex.org/W2914621247","https://openalex.org/W3017143921","https://openalex.org/W4240908132","https://openalex.org/W4247346926","https://openalex.org/W4254721730","https://openalex.org/W4255459561","https://openalex.org/W4302377426","https://openalex.org/W6630874621","https://openalex.org/W6635193281","https://openalex.org/W6670271065","https://openalex.org/W6678701036","https://openalex.org/W6680134797","https://openalex.org/W6680971561","https://openalex.org/W6682602269","https://openalex.org/W6776565550","https://openalex.org/W6844488333","https://openalex.org/W6902931378","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Text":[0],"is":[1,118],"ubiquitous":[2],"and,":[3],"not":[4],"surprisingly,":[5],"many":[6],"important":[7,258],"applications":[8,24],"rely":[9],"on":[10,103,123,203],"textual":[11],"data":[12,265],"for":[13,47,54,143,186,220,236,256],"a":[14,19,56,100,182,237,252],"variety":[15],"of":[16,80,113,140,165,199,207],"tasks.":[17],"As":[18],"notable":[20],"example,":[21,33],"information":[22],"extraction":[23],"derive":[25],"structured":[26],"relations":[27],"from":[28,175],"unstructured":[29],"text;":[30],"as":[31],"another":[32],"focused":[34],"crawlers":[35],"explore":[36],"the":[37,65,78,138,187,194,197,200,208,222,231],"web":[38],"to":[39,136,157,180],"locate":[40],"pages":[41],"about":[42],"specific":[43],"topics.":[44],"Execution":[45],"plans":[46,97,142,162,201,235],"text-centric":[48,144,259],"tasks":[49,145,260],"follow":[50],"two":[51],"general":[52],"paradigms":[53],"processing":[55],"text":[57,66,210],"database:":[58],"either":[59],"we":[60,70,131,154],"can":[61,71,98],"scan,":[62],"or":[63,125],"'crawl,\"":[64],"database":[67],"or,":[68],"alternatively,":[69],"exploit":[72],"search":[73],"engine":[74],"indexes":[75],"and":[76,94,107,121,160,169,178,216,243,261],"retrieve":[77],"documents":[79],"interest":[81],"via":[82],"carefully":[83],"crafted":[84],"queries":[85],"constructed":[86],"in":[87,111,146,163,240],"task-specific":[88,205],"ways.":[89],"The":[90],"choice":[91,117,139],"between":[92],"crawl-":[93],"query-based":[95],"execution":[96,105,141,167,188,234],"have":[99],"substantial":[101],"impact":[102],"both":[104,166],"time":[106,168],"output":[108,170,244],"\"completeness\"":[109],"(e.g.,":[110],"terms":[112,164],"recall).":[114],"Nevertheless,":[115],"this":[116,129,152],"typically":[119],"ad-hoc":[120],"based":[122],"heuristics":[124],"plain":[126],"intuition.":[127],"In":[128],"paper,":[130],"present":[132,217],"fundamental":[133,204],"building":[134],"blocks":[135],"make":[137],"an":[147],"informed,":[148],"cost-based":[149],"way.":[150],"Towards":[151],"goal,":[153],"show":[155],"how":[156],"analyze":[158],"query-":[159],"crawl-based":[161],"completeness.":[171],"We":[172,212,247],"adapt":[173],"results":[174,250],"random-graph":[176],"theory":[177],"statistics":[179],"develop":[181],"rigorous":[183],"cost":[184,191],"model":[185,192],"plans.":[189],"Our":[190],"reflects":[193],"fact":[195],"that":[196],"performance":[198],"depends":[202],"properties":[206,215],"underlying":[209],"databases.":[211],"identify":[213],"these":[214],"efficient":[218],"techniques":[219],"estimating":[221],"associated":[223],"cost-model":[224],"parameters.":[225],"Overall,":[226],"our":[227,249],"approach":[228],"helps":[229],"predict":[230],"most":[232],"appropriate":[233],"task,":[238],"resulting":[239],"significant":[241],"efficiency":[242],"completeness":[245],"benefits.":[246],"complement":[248],"with":[251],"large-scale":[253],"experimental":[254],"evaluation":[255],"three":[257],"over":[262],"multiple":[263],"real-life":[264],"sets.":[266]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":6}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}