{"id":"https://openalex.org/W2321923054","doi":"https://doi.org/10.1145/2837185.2837208","title":"Towards complete coverage in focused web harvesting","display_name":"Towards complete coverage in focused web harvesting","publication_year":2015,"publication_date":"2015-12-11","ids":{"openalex":"https://openalex.org/W2321923054","doi":"https://doi.org/10.1145/2837185.2837208","mag":"2321923054"},"language":"en","primary_location":{"id":"doi:10.1145/2837185.2837208","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837185.2837208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ris.utwente.nl/ws/files/286124518/Kkelghati2015towards.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080038825","display_name":"Mohammadreza Khelghati","orcid":null},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Mohammadreza Khelghati","raw_affiliation_strings":["University of Twente, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Twente, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108167267","display_name":"Djoerd Hiemstra","orcid":"https://orcid.org/0000-0003-4967-2900"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Djoerd Hiemstra","raw_affiliation_strings":["University of Twente, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Twente, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062035687","display_name":"Maurice van Keulen","orcid":"https://orcid.org/0000-0003-2436-1372"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maurice van Keulen","raw_affiliation_strings":["University of Twente, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Twente, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080038825"],"corresponding_institution_ids":["https://openalex.org/I94624287"],"apc_list":null,"apc_paid":null,"fwci":1.6588,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89362105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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/T11550","display_name":"Text and Document Classification Technologies","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9922999739646912,"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":0.8373172283172607},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.7777495384216309},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7654098272323608},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7535321712493896},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.704925000667572},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5932151079177856},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5725145936012268},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5135877132415771},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.5051830410957336},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.39016151428222656},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06580296158790588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373172283172607},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.7777495384216309},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7654098272323608},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7535321712493896},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.704925000667572},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5932151079177856},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5725145936012268},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5135877132415771},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.5051830410957336},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39016151428222656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06580296158790588},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2837185.2837208","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837185.2837208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire/7da698d5-5c31-4561-954c-be1d077e6ecf","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/7da698d5-5c31-4561-954c-be1d077e6ecf","pdf_url":"https://ris.utwente.nl/ws/files/286124518/Kkelghati2015towards.pdf","source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Khelghati, M, Hiemstra, D & van Keulen, M 2015, Towards Complete Coverage in Focused Web Harvesting. in Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services (iiWAS 2015). Association for Computing Machinery, New York, pp. 65, 17th International Conference on Information Integration and Web-based Applications & Services, IIWAS 2015, Brussels, Belgium, 11/12/15. https://doi.org/10.1145/2837185.2837208","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/227672","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/227672","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Indrawan-Santiago, M. (ed.), iiWAS2015:17th International Conference on Information Integration and Web-Based Applications and Services, iiWAS 2015, 11-13 December 2015, Brussels, Belgium - Proceedings, pp. 1-9","raw_type":"Article in monograph or in proceedings"},{"id":"pmh:oai:ris.utwente.nl:publications/7da698d5-5c31-4561-954c-be1d077e6ecf","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:ris.utwente.nl:openaire/7da698d5-5c31-4561-954c-be1d077e6ecf","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/7da698d5-5c31-4561-954c-be1d077e6ecf","pdf_url":"https://ris.utwente.nl/ws/files/286124518/Kkelghati2015towards.pdf","source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Khelghati, M, Hiemstra, D & van Keulen, M 2015, Towards Complete Coverage in Focused Web Harvesting. in Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services (iiWAS 2015). Association for Computing Machinery, New York, pp. 65, 17th International Conference on Information Integration and Web-based Applications & Services, IIWAS 2015, Brussels, Belgium, 11/12/15. https://doi.org/10.1145/2837185.2837208","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2321923054.pdf","grobid_xml":"https://content.openalex.org/works/W2321923054.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W129956923","https://openalex.org/W1532325895","https://openalex.org/W1605217017","https://openalex.org/W1970173714","https://openalex.org/W1986828474","https://openalex.org/W1993692165","https://openalex.org/W2032475771","https://openalex.org/W2036181041","https://openalex.org/W2101302356","https://openalex.org/W2104049510","https://openalex.org/W2118356300","https://openalex.org/W2136059419","https://openalex.org/W2148738951","https://openalex.org/W2151007976","https://openalex.org/W2155030693","https://openalex.org/W2170971772","https://openalex.org/W2173431721","https://openalex.org/W2177379877"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2901901036","https://openalex.org/W2026738364","https://openalex.org/W1521725692","https://openalex.org/W2093300859","https://openalex.org/W3008917487","https://openalex.org/W2124814993","https://openalex.org/W2013069866","https://openalex.org/W3197639690","https://openalex.org/W2363322605"],"abstract_inverted_index":{"With":[0],"the":[1,77,88,94,137,144,155,181],"goal":[2],"of":[3,63,66,76,90,96,146,184],"harvesting":[4],"all":[5,18,35,75],"information":[6,36,126,162,164],"about":[7,37],"a":[8,22,27,60,83,120,129,133,166],"given":[9,23,84,130,136],"entity,":[10],"in":[11,50,104,110],"this":[12,116,160],"paper,":[13],"we":[14,118],"try":[15],"to":[16,33,128,150],"harvest":[17],"matching":[19,78],"documents":[20,92,186],"for":[21,38,82,108],"query":[24,79,131],"submitted":[25],"on":[26,178],"search":[28,51,68,80,134,138],"engine.":[29],"The":[30,141,170],"objective":[31],"is":[32],"retrieve":[34],"instance":[39,109],"\"Michael":[40],"Jackson\",":[41],"\"Islamic":[42],"State\",":[43],"or":[44,53],"\"FC":[45],"Barcelona\"":[46],"from":[47,132,165],"indexed":[48],"data":[49,55],"engines,":[52],"hidden":[54],"behind":[56],"web":[57,67,106],"forms,":[58],"using":[59],"minimum":[61],"number":[62,89,95,145,183],"queries.":[64],"Policies":[65],"engines":[69],"usually":[70],"do":[71],"not":[72],"allow":[73],"accessing":[74],"results":[81,157],"query.":[85,189],"They":[86],"limit":[87],"returned":[91],"and":[93,158],"user":[97],"requests.":[98],"These":[99],"limitations":[100],"are":[101],"also":[102],"applied":[103],"deep":[105],"sources,":[107],"social":[111],"networks":[112],"like":[113],"Twitter.":[114],"In":[115],"work,":[117],"propose":[119],"new":[121,171],"approach":[122,142,172],"which":[123],"automatically":[124],"collects":[125],"related":[127],"engine,":[135],"engine's":[139],"limitations.":[140],"minimizes":[143],"queries":[147],"that":[148],"need":[149],"be":[151],"sent":[152],"by":[153],"analysing":[154],"retrieved":[156],"combining":[159],"analysed":[161],"with":[163],"large":[167],"external":[168],"corpus.":[169],"outperforms":[173],"existing":[174],"approaches":[175],"when":[176],"tested":[177],"Google,":[179],"measuring":[180],"total":[182],"unique":[185],"found":[187],"per":[188]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2016-06-24T00:00:00"}