{"id":"https://openalex.org/W1984968692","doi":"https://doi.org/10.1145/2063576.2063687","title":"Focusing on novelty","display_name":"Focusing on novelty","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W1984968692","doi":"https://doi.org/10.1145/2063576.2063687","mag":"1984968692"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","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/A5000683692","display_name":"Luciano Barbosa","orcid":"https://orcid.org/0000-0002-6858-4773"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luciano Barbosa","raw_affiliation_strings":["AT&amp;T Labs -- Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs -- Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111475783","display_name":"Srinivas Bangalore","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Bangalore","raw_affiliation_strings":["AT&amp;T Labs -- Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs -- Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"755","last_page":"764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965999722480774,"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":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.8456975221633911},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8371905088424683},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.7186444997787476},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.703931987285614},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6936764717102051},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5559607744216919},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5436763763427734},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5250275731086731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5225574374198914},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5195406079292297},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4968462288379669},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4749874174594879},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4389798939228058},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3399399518966675},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.14958378672599792},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.091071218252182}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456975221633911},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8371905088424683},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.7186444997787476},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.703931987285614},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6936764717102051},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5559607744216919},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5436763763427734},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5250275731086731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5225574374198914},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5195406079292297},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4968462288379669},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4749874174594879},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4389798939228058},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3399399518966675},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.14958378672599792},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.091071218252182},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2063576.2063687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W151364351","https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W1494910745","https://openalex.org/W1509214810","https://openalex.org/W1665921526","https://openalex.org/W1850668662","https://openalex.org/W1993320088","https://openalex.org/W1996718000","https://openalex.org/W1998284155","https://openalex.org/W2005579877","https://openalex.org/W2017726337","https://openalex.org/W2020073413","https://openalex.org/W2104009457","https://openalex.org/W2105588112","https://openalex.org/W2110034127","https://openalex.org/W2111604701","https://openalex.org/W2124673015","https://openalex.org/W2133990480","https://openalex.org/W2135322081","https://openalex.org/W2136780519","https://openalex.org/W2154103141","https://openalex.org/W2164666834","https://openalex.org/W2165861304","https://openalex.org/W2169657490","https://openalex.org/W4254373586","https://openalex.org/W6629637077","https://openalex.org/W6678701036"],"related_works":["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","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Word":[0],"prediction":[1],"performed":[2],"by":[3,87,181,212,220],"language":[4,39,64,81,175],"models":[5,176],"has":[6,29],"an":[7,103],"important":[8],"role":[9],"in":[10,59,78,97,118,121,155,159,185,198,225,258],"many":[11],"tasks":[12],"as":[13,147],"e.g.":[14],"word":[15],"sense":[16],"disambiguation,":[17],"speech":[18,190],"recognition,":[19,21],"hand-writing":[20],"query":[22,25],"spelling":[23],"and":[24,111],"segmentation.":[26],"Recent":[27],"research":[28],"exploited":[30],"the":[31,35,70,75,79,98,148,178,186,210,217,221,226,251,254,259,278],"textual":[32],"content":[33,231,257],"of":[34,136,188,193,216],"Web":[36,53],"to":[37,51,61,73,107,116,123,143,205,209,234,249,269],"create":[38,62],"models.":[40,65],"In":[41,66,196],"this":[42],"paper,":[43],"we":[44,167,239],"propose":[45],"a":[46,133,182,189],"new":[47],"focused":[48],"crawling":[49,68,213],"strategy":[50],"collect":[52],"pages":[54,90,117,218,276],"that":[55,169,241,264],"focuses":[56],"on":[57,102,271],"novelty":[58],"order":[60,122],"diverse":[63],"each":[67],"cycle,":[69],"crawler":[71,138,184,202,244,252],"tries":[72],"ll":[74],"gaps":[76,110],"present":[77],"current":[80],"model":[82],"built":[83],"from":[84],"previous":[85],"cycles,":[86],"avoiding":[88,229],"visiting":[89],"whose":[91],"vocabulary":[92],"is":[93,140],"already":[94],"well":[95],"represented":[96],"model.":[99],"It":[100],"relies":[101],"information":[104],"theoretic":[105],"measure":[106],"identify":[108],"these":[109,119],"then":[112],"learns":[113],"link":[114],"patterns":[115],"regions":[120],"guide":[124,250],"its":[125,141,145],"visitation":[126],"policy.":[127],"To":[128],"handle":[129],"constantly":[130],"evolving":[131],"domains,":[132],"key":[134],"feature":[135],"our":[137,153,161,170,201,242,265],"approach":[139,154,171,266],"ability":[142],"adjust":[144],"focus":[146],"crawl":[149],"progresses.":[150],"We":[151],"evaluate":[152],"two":[156],"different":[157],"scenarios":[158],"which":[160],"solution":[162],"can":[163,245],"be":[164,247],"useful.":[165],"First,":[166],"demonstrate":[168],"produces":[172],"more":[173,274],"effective":[174],"than":[177,277],"ones":[179],"created":[180],"baseline":[183,211,279],"context":[187],"recognition":[191],"task":[192],"broadcast":[194],"news.":[195,260],"fact,":[197],"some":[199],"cases,":[200],"was":[203,267],"able":[204,268],"obtain":[206,270],"similar":[207],"results":[208,262],"only":[214],"12.5%":[215],"collected":[219],"latter.":[222],"Secondly,":[223],"since":[224],"news":[227],"domain":[228],"well-represented":[230],"might":[232],"lead":[233],"novelty,":[235],"i.e.":[236],"up-to-date":[237,275],"pages,":[238],"show":[240,263],"diversity-based":[243],"also":[246],"helpful":[248],"for":[253],"most":[255],"recent":[256],"The":[261],"average":[272],"50%":[273],"crawler.":[280]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
