{"id":"https://openalex.org/W2158420658","doi":"https://doi.org/10.1145/2661829.2661902","title":"Focused Crawling for Structured Data","display_name":"Focused Crawling for Structured Data","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2158420658","doi":"https://doi.org/10.1145/2661829.2661902","mag":"2158420658"},"language":"en","primary_location":{"id":"doi:10.1145/2661829.2661902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2661902","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 ACM International Conference on Conference on Information and Knowledge Management","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/A5047915112","display_name":"Robert Meusel","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Robert Meusel","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036340022","display_name":"Peter Mika","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Peter Mika","raw_affiliation_strings":["Yahoo Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021439660","display_name":"Roi Blanco","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Roi Blanco","raw_affiliation_strings":["Yahoo Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047915112"],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":9.8166,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97770923,"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":"1039","last_page":"1048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9869999885559082,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8539158701896667},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8284145593643188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8086012005805969},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7305809259414673},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6553144454956055},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6454156637191772},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6286087036132812},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.579587459564209},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5299310088157654},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5155044198036194},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5058293342590332},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.4924112558364868},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4860561192035675},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.43236157298088074},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.42310625314712524},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.33410149812698364},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.19657739996910095}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8539158701896667},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8284145593643188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086012005805969},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7305809259414673},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6553144454956055},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6454156637191772},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6286087036132812},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.579587459564209},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5299310088157654},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5155044198036194},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5058293342590332},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.4924112558364868},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4860561192035675},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.43236157298088074},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.42310625314712524},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.33410149812698364},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.19657739996910095},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2661829.2661902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2661902","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 ACM International Conference on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W3540556","https://openalex.org/W100539920","https://openalex.org/W125867323","https://openalex.org/W183313898","https://openalex.org/W1489992655","https://openalex.org/W1504010199","https://openalex.org/W1514736499","https://openalex.org/W1532325895","https://openalex.org/W1583544304","https://openalex.org/W1854214752","https://openalex.org/W1999740339","https://openalex.org/W2000273502","https://openalex.org/W2003471189","https://openalex.org/W2005579877","https://openalex.org/W2008781077","https://openalex.org/W2017726337","https://openalex.org/W2028138594","https://openalex.org/W2055950890","https://openalex.org/W2108738385","https://openalex.org/W2110034127","https://openalex.org/W2112420033","https://openalex.org/W2112490010","https://openalex.org/W2112572459","https://openalex.org/W2119012894","https://openalex.org/W2124673015","https://openalex.org/W2133433261","https://openalex.org/W2135335717","https://openalex.org/W2140018945","https://openalex.org/W2146429536","https://openalex.org/W2158807713","https://openalex.org/W2164284962","https://openalex.org/W2270949707","https://openalex.org/W2296563174","https://openalex.org/W2394815666","https://openalex.org/W2402098033","https://openalex.org/W2604272474","https://openalex.org/W2902404196","https://openalex.org/W3000138670","https://openalex.org/W3003253354","https://openalex.org/W3141358367","https://openalex.org/W6600156376","https://openalex.org/W6676077707","https://openalex.org/W6712670493","https://openalex.org/W6940889055"],"related_works":["https://openalex.org/W2095543197","https://openalex.org/W2402678663","https://openalex.org/W3201526811","https://openalex.org/W4200125296","https://openalex.org/W2379145789","https://openalex.org/W1994958611","https://openalex.org/W2277785728","https://openalex.org/W2610451498","https://openalex.org/W2109463504","https://openalex.org/W3199173531"],"abstract_inverted_index":{"The":[0],"Web":[1],"is":[2],"rapidly":[3],"transforming":[4],"from":[5,129,134],"a":[6,102,162],"pure":[7],"document":[8],"collection":[9],"to":[10,26,43,112],"the":[11,61,75,119,122,130,152],"largest":[12],"connected":[13],"public":[14],"data":[15,30,67],"space.":[16],"Semantic":[17],"annotations":[18],"of":[19,64,86,105,121,132,154],"web":[20,115],"pages":[21,94,116,156,159],"make":[22],"it":[23],"notably":[24],"easier":[25],"extract":[27],"and":[28,31,39,108,157],"reuse":[29],"are":[32],"increasingly":[33],"used":[34],"by":[35],"both":[36],"search":[37,46],"engines":[38],"social":[40],"media":[41],"sites":[42],"provide":[44],"better":[45],"experiences":[47],"through":[48],"rich":[49],"snippets,":[50],"faceted":[51],"search,":[52],"task":[53],"completion,":[54],"etc.":[55],"In":[56,98],"our":[57],"work,":[58],"we":[59,100],"study":[60],"novel":[62,103],"problem":[63],"crawling":[65,88],"structured":[66],"embedded":[68],"inside":[69],"HTML":[70],"pages.":[71,137],"We":[72,82,138],"describe":[73],"Anthelion,":[74],"first":[76],"focused":[77,87,148],"crawler":[78],"addressing":[79],"this":[80],"task.":[81],"propose":[83,101],"new":[84],"methods":[85],"specifically":[89],"designed":[90],"for":[91,147],"collecting":[92],"data-rich":[93,114],"with":[95],"greater":[96],"efficiency.":[97],"particular,":[99],"combination":[104],"online":[106],"learning":[107],"bandit-based":[109],"explore/exploit":[110],"approaches":[111,146],"predict":[113],"based":[117],"on":[118],"context":[120],"page":[123],"as":[124,126,151],"well":[125],"using":[127],"feedback":[128],"extraction":[131],"metadata":[133],"previously":[135],"seen":[136],"show":[139],"that":[140],"these":[141],"techniques":[142],"significantly":[143],"outperform":[144],"state-of-the-art":[145],"crawling,":[149],"measured":[150],"ratio":[153],"relevant":[155],"non-relevant":[158],"collected":[160],"within":[161],"given":[163],"budget.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
