{"id":"https://openalex.org/W2076094024","doi":"https://doi.org/10.1145/1774088.1774459","title":"Addressing the limited scope problem of focused crawling using a result merging approach","display_name":"Addressing the limited scope problem of focused crawling using a result merging approach","publication_year":2010,"publication_date":"2010-03-22","ids":{"openalex":"https://openalex.org/W2076094024","doi":"https://doi.org/10.1145/1774088.1774459","mag":"2076094024"},"language":"en","primary_location":{"id":"doi:10.1145/1774088.1774459","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","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/A5043509852","display_name":"Ari Pirkola","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Ari Pirkola","raw_affiliation_strings":["University of Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026174345","display_name":"Tuomas Talvensaari","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Talvensaari","raw_affiliation_strings":["University of Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043509852"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":2.7748,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92640376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1735","last_page":"1740"},"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/T11478","display_name":"Caching and Content Delivery","score":0.989300012588501,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9739000201225281,"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/crawling","display_name":"Crawling","score":0.983568549156189},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.7377249002456665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7373839020729065},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5744607448577881},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5310210585594177},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4559318721294403},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44878673553466797},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38219866156578064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07183215022087097},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06188437342643738}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.983568549156189},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.7377249002456665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373839020729065},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5744607448577881},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5310210585594177},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4559318721294403},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44878673553466797},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38219866156578064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07183215022087097},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06188437342643738},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1774088.1774459","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8118091828","display_name":null,"funder_award_id":"1.26E+17","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W48945287","https://openalex.org/W109995334","https://openalex.org/W1481372933","https://openalex.org/W1489992655","https://openalex.org/W2037796960","https://openalex.org/W2045998703","https://openalex.org/W2088123540","https://openalex.org/W2100612254","https://openalex.org/W2121354841","https://openalex.org/W2124673015","https://openalex.org/W2128915886","https://openalex.org/W2140214528","https://openalex.org/W2142211218","https://openalex.org/W2560674852","https://openalex.org/W4205241946","https://openalex.org/W4239729368"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2026661369"],"abstract_inverted_index":{"Focused":[0],"crawling":[1,35,51,55,64,74],"refers":[2],"to":[3,18,30],"a":[4,57],"process":[5],"of":[6,34,49,53,63,86,105],"fetching":[7],"domain-specific":[8,20],"pages":[9],"from":[10,26],"the":[11,31,47,84,103],"Web.":[12],"It":[13],"is":[14],"an":[15],"important":[16],"method":[17],"build":[19],"document":[21],"collections,":[22],"but":[23],"it":[24],"suffers":[25],"low":[27],"recall":[28],"due":[29],"local":[32],"nature":[33],"algorithms":[36],"associated":[37],"with":[38],"Web's":[39],"community":[40],"structure.":[41],"In":[42],"this":[43],"study,":[44],"we":[45],"address":[46],"problem":[48],"limited":[50],"scope":[52],"focused":[54,73,87],"using":[56],"result":[58],"merging":[59,81],"approach.":[60],"The":[61,89],"results":[62,90],"processes":[65],"based":[66,94],"on":[67,95],"different":[68],"start":[69],"URL":[70],"sets":[71],"and":[72,99,107],"methods":[75],"were":[76],"merged.":[77],"We":[78],"found":[79],"that":[80],"improves":[82],"considerably":[83],"effectiveness":[85],"crawling.":[88],"reported":[91],"here":[92],"are":[93],"10":[96],"test":[97],"topics":[98],"140":[100],"crawls":[101],"in":[102],"domains":[104],"genomics":[106],"genetics.":[108]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
