{"id":"https://openalex.org/W2208078047","doi":"https://doi.org/10.1109/bigdata.2015.7363976","title":"Optimizing apache nutch for domain specific crawling at large scale","display_name":"Optimizing apache nutch for domain specific crawling at large scale","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2208078047","doi":"https://doi.org/10.1109/bigdata.2015.7363976","mag":"2208078047"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big 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/A5016928206","display_name":"Lu\u00eds Alfonso Ure\u00f1a L\u00f3pez","orcid":"https://orcid.org/0000-0001-7540-4059"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luis A. Lopez","raw_affiliation_strings":["NSIDC, Boulder, Colorado"],"affiliations":[{"raw_affiliation_string":"NSIDC, Boulder, Colorado","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruth Duerr","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147267","display_name":"Ronin Institute","ror":"https://ror.org/04awze035","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210147267"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruth Duerr","raw_affiliation_strings":["The Ronin Institute, Boulder, Colorado"],"affiliations":[{"raw_affiliation_string":"The Ronin Institute, Boulder, Colorado","institution_ids":["https://openalex.org/I4210147267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021015320","display_name":"S. S. Khalsa","orcid":"https://orcid.org/0000-0001-9217-5550"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siri Jodha Singh Khalsa","raw_affiliation_strings":["University of Colorado Boulder, Boulder, CO, US"],"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder, Boulder, CO, US","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016928206"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0512,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81264122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"54","issue":null,"first_page":"1967","last_page":"1971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9937999844551086,"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":0.9923999905586243,"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/crawling","display_name":"Crawling","score":0.8574777841567993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7514688372612},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6052659749984741},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5614883899688721},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5281075239181519},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5095551013946533},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5022692680358887},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4963396191596985},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40047112107276917},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3715672194957733},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3685535192489624},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14293703436851501}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8574777841567993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7514688372612},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6052659749984741},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5614883899688721},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5281075239181519},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5095551013946533},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5022692680358887},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4963396191596985},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40047112107276917},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3715672194957733},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3685535192489624},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14293703436851501},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","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":9,"referenced_works":["https://openalex.org/W41359776","https://openalex.org/W2016708390","https://openalex.org/W2039157918","https://openalex.org/W2112396605","https://openalex.org/W2115461474","https://openalex.org/W2124673015","https://openalex.org/W2155072926","https://openalex.org/W2159185913","https://openalex.org/W2171266073"],"related_works":["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/W2089702591","https://openalex.org/W4255854114"],"abstract_inverted_index":{"Focused":[0,22],"crawls":[1,23],"are":[2],"key":[3],"to":[4,12,28,91],"acquiring":[5],"data":[6,65],"at":[7,70],"large":[8],"scale":[9,35],"in":[10],"order":[11],"implement":[13],"systems":[14],"like":[15],"domain":[16],"search":[17],"engines":[18],"and":[19,66,84,88,97],"knowledge":[20],"databases.":[21],"introduce":[24],"non":[25],"trivial":[26],"problems":[27],"the":[29,49],"already":[30],"difficult":[31],"problem":[32],"of":[33,40,48,61,81,94,103],"web":[34,67],"crawling;":[36],"To":[37],"address":[38],"some":[39],"these":[41],"issues,":[42],"BCube":[43],"-":[44,55],"a":[45,58,78,100],"building":[46],"block":[47],"National":[50],"Science":[51],"Foundation's":[52],"EarthCube":[53],"program":[54],"has":[56],"developed":[57],"tailored":[59],"version":[60,80],"Apache":[62,82],"Nutch":[63,83],"for":[64],"services":[68],"discovery":[69],"scale.":[71],"We":[72],"describe":[73],"how":[74,85],"we":[75,86],"started":[76],"with":[77],"vanilla":[79],"optimized":[87],"scaled":[89],"it":[90],"reach":[92],"gigabytes":[93],"discovered":[95],"links":[96],"almost":[98],"half":[99],"billion":[101],"documents":[102],"interest":[104],"crawled":[105],"so":[106],"far.":[107]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}