{"id":"https://openalex.org/W2798520647","doi":"https://doi.org/10.1145/3183713.3193569","title":"Deeper","display_name":"Deeper","publication_year":2018,"publication_date":"2018-05-25","ids":{"openalex":"https://openalex.org/W2798520647","doi":"https://doi.org/10.1145/3183713.3193569","mag":"2798520647"},"language":"en","primary_location":{"id":"doi:10.1145/3183713.3193569","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3193569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 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/A5100462619","display_name":"Pei Wang","orcid":"https://orcid.org/0000-0001-9066-3948"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Pei Wang","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590823","display_name":"Yongjun He","orcid":"https://orcid.org/0009-0002-5901-0388"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongjun He","raw_affiliation_strings":["Nanjing University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Burnaby, BC, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051613770","display_name":"Ryan Shea","orcid":"https://orcid.org/0000-0002-8213-2036"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ryan Shea","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University, Simon Fraser University, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Columbia University, Simon Fraser University, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100462619"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":1.5707,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87574078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1801","last_page":"1804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9934999942779541,"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/crawling","display_name":"Crawling","score":0.8532037138938904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8458914756774902},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5335557460784912},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5155284404754639},{"id":"https://openalex.org/keywords/semi-structured-data","display_name":"Semi-structured data","score":0.4528062343597412},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.44621098041534424},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44476425647735596},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.443510502576828},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34210067987442017},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.243971049785614},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.16556978225708008}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8532037138938904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458914756774902},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5335557460784912},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5155284404754639},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.4528062343597412},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.44621098041534424},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44476425647735596},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.443510502576828},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34210067987442017},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.243971049785614},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.16556978225708008},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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:10.1145/3183713.3193569","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3193569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1792735297","https://openalex.org/W1989361423","https://openalex.org/W1989856433","https://openalex.org/W1996505782","https://openalex.org/W2043499927","https://openalex.org/W2064853889","https://openalex.org/W2104042955","https://openalex.org/W2140116426","https://openalex.org/W2293940046","https://openalex.org/W2294768397","https://openalex.org/W2949047719"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2384770049"],"abstract_inverted_index":{"Data":[0,13],"scientists":[1,113],"often":[2],"spend":[3],"more":[4,71],"than":[5,172],"80%":[6],"of":[7,17,79,87,91,107,186],"their":[8],"time":[9],"on":[10,45],"data":[11,27,36,63,97,112,179,232],"preparation.":[12],"enrichment,":[14],"the":[15,31,85,88,102,129,133,136,167,174,178,184,199,211,237,244],"act":[16],"extending":[18],"a":[19,61,70,96,116,120,142,149,156,219],"local":[20,89,117,130],"database":[21,90,118,122,131,170,221],"with":[22,132],"new":[23,193],"attributes":[24,134],"from":[25,135,155],"external":[26],"sources,":[28],"is":[29,109,145,153,164,229,241],"among":[30],"most":[32],"time-consuming":[33],"tasks.":[34],"Existing":[35],"enrichment":[37,98,180,233],"works":[38],"are":[39],"resource":[40],"intensive:":[41],"data-intensive":[42],"by":[43,52,58,101],"relying":[44],"web":[46,80,159],"tables":[47],"or":[48,56],"knowledge":[49],"bases,":[50],"monetarily-intensive":[51],"purchasing":[53],"entire":[54,168],"datasets,":[55],"time-intensive":[57],"fully":[59],"crawling":[60,160,194,239],"web-based":[62],"source.":[64],"In":[65],"this":[66],"work,":[67],"we":[68,213],"explore":[69],"targeted":[72],"alternative":[73],"that":[74,124,141,226],"uses":[75],"resources":[76],"(in":[77],"terms":[78],"API":[81],"calls)":[82],"proportional":[83],"to":[84,110,114,119,147,165,177,206,217,224,243],"size":[86],"interest.":[92],"We":[93,139,182,196],"build":[94],"Deeper,":[95],"system":[99,201],"powered":[100],"deep":[103,158],"web.":[104],"The":[105],"goal":[106,163],"Deeper":[108,200,216,228],"help":[111],"link":[115],"hidden":[121,137,150,169],"so":[123],"they":[125],"can":[126],"easily":[127],"enrich":[128,218],"database.":[138,151],"find":[140],"challenging":[143],"problem":[144],"how":[146,205],"crawl":[148,166],"This":[152],"different":[154],"typical":[157],"problem,":[161],"whose":[162],"rather":[171],"only":[173],"content":[175],"relating":[176],"task.":[181],"demonstrate":[183],"limitations":[185],"straightforward":[187,245],"solutions":[188],"and":[189,203,222,235],"propose":[190],"an":[191,230],"effective":[192],"strategy.":[195],"also":[197],"present":[198],"architecture":[202],"discuss":[204],"implement":[207],"each":[208],"component.":[209],"During":[210],"demo,":[212],"will":[214],"use":[215],"publication":[220],"aim":[223],"show":[225],"(1)":[227],"end-to-end":[231],"solution,":[234],"(2)":[236],"proposed":[238],"strategy":[240],"superior":[242],"ones.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-05-07T00:00:00"}
