{"id":"https://openalex.org/W2520254100","doi":"https://doi.org/10.1145/3011141.3011198","title":"Efficient web harvesting strategies for monitoring deep web content","display_name":"Efficient web harvesting strategies for monitoring deep web content","publication_year":2016,"publication_date":"2016-11-28","ids":{"openalex":"https://openalex.org/W2520254100","doi":"https://doi.org/10.1145/3011141.3011198","mag":"2520254100"},"language":"en","primary_location":{"id":"doi:10.1145/3011141.3011198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3011141.3011198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Information Integration and Web-based Applications and 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/286122508/iiwas_efficient.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091530242","display_name":"Mohammad 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":false,"raw_author_name":"Mohammad Khelghati","raw_affiliation_strings":["University of Twente, Netherlands"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94624287"],"apc_list":null,"apc_paid":null,"fwci":0.6766,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79895601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"389","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9883000254631042,"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/T11478","display_name":"Caching and Content Delivery","score":0.9732000231742859,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8364472389221191},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6087257862091064},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.6047084927558899},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5905877947807312},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5158666968345642},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5007960796356201},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49416211247444153},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4712681472301483},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4369291663169861},{"id":"https://openalex.org/keywords/web-analytics","display_name":"Web analytics","score":0.4367332458496094},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42872852087020874},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.42180508375167847},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.372962087392807},{"id":"https://openalex.org/keywords/web-application-security","display_name":"Web application security","score":0.29120028018951416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8364472389221191},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6087257862091064},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.6047084927558899},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5905877947807312},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5158666968345642},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5007960796356201},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49416211247444153},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4712681472301483},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4369291663169861},{"id":"https://openalex.org/C516187249","wikidata":"https://www.wikidata.org/wiki/Q10719477","display_name":"Web analytics","level":5,"score":0.4367332458496094},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42872852087020874},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.42180508375167847},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.372962087392807},{"id":"https://openalex.org/C59241245","wikidata":"https://www.wikidata.org/wiki/Q4781497","display_name":"Web application security","level":4,"score":0.29120028018951416},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3011141.3011198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3011141.3011198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Information Integration and Web-based Applications and Services","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire/8e5acddb-d800-4630-965c-034f1232c31a","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/8e5acddb-d800-4630-965c-034f1232c31a","pdf_url":"https://ris.utwente.nl/ws/files/286122508/iiwas_efficient.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 2016, Efficient Web Harvesting Strategies for Monitoring Deep Web Content. in Proceedings of the 18th International Conference on Information Integration and Web-based Applications & Services (iiWAS 2016). Association for Computing Machinery, New York, pp. 389-393. https://doi.org/10.1145/3011141.3011198","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/226363","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/226363","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.), iiWAS2016: The 18th International Conference on Information Integration and Web-based Applications &amp; Services November 28 - 30, 2016, Singapore, pp. 389-393","raw_type":"Article in monograph or in proceedings"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/226364","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/226364","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":"<dc:source>https://research.utwente.nl/files/5122955/Efficient_Web_Harvesting_Strategies.pdf","raw_type":"External research report"},{"id":"pmh:oai:ris.utwente.nl:publications/f87404bf-3174-4ca5-9d72-77927e9db44c","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/f87404bf-3174-4ca5-9d72-77927e9db44c","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/8e5acddb-d800-4630-965c-034f1232c31a","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/8e5acddb-d800-4630-965c-034f1232c31a","pdf_url":"https://ris.utwente.nl/ws/files/286122508/iiwas_efficient.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 2016, Efficient Web Harvesting Strategies for Monitoring Deep Web Content. in Proceedings of the 18th International Conference on Information Integration and Web-based Applications & Services (iiWAS 2016). Association for Computing Machinery, New York, pp. 389-393. https://doi.org/10.1145/3011141.3011198","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2520254100.pdf","grobid_xml":"https://content.openalex.org/works/W2520254100.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W129956923","https://openalex.org/W1485321296","https://openalex.org/W1510756095","https://openalex.org/W1566984846","https://openalex.org/W1571075834","https://openalex.org/W1605217017","https://openalex.org/W1659541576","https://openalex.org/W1964698713","https://openalex.org/W1993692165","https://openalex.org/W2030453570","https://openalex.org/W2032475771","https://openalex.org/W2052889856","https://openalex.org/W2059713800","https://openalex.org/W2094930182","https://openalex.org/W2112923539","https://openalex.org/W2140336868","https://openalex.org/W2142211218","https://openalex.org/W2148738951","https://openalex.org/W2170971772","https://openalex.org/W2177379877","https://openalex.org/W2321923054","https://openalex.org/W2469164273","https://openalex.org/W2561675875","https://openalex.org/W2914994274","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W68102627","https://openalex.org/W2928320532","https://openalex.org/W4385976368","https://openalex.org/W1839266913","https://openalex.org/W3174013239","https://openalex.org/W2406286368","https://openalex.org/W2493908403","https://openalex.org/W4386050420","https://openalex.org/W4386050419","https://openalex.org/W1986870096"],"abstract_inverted_index":{"Web":[0,7],"content":[1,130,166,195],"changes":[2,80,111],"rapidly":[3],"[18].":[4],"In":[5,118],"Focused":[6],"Harvesting":[8],"[17]":[9],"which":[10],"aim":[11],"it":[12],"is":[13],"to":[14,35,45,70,91,131,144],"achieve":[15],"a":[16,20,37,53,60,63,113,132,152,162,168,175,200],"complete":[17],"harvest":[18,146],"for":[19,31,112,199],"given":[21,114,133,153,201],"topic,":[22,64],"this":[23,119],"dynamic":[24],"nature":[25],"of":[26,39,48,95],"the":[27,41,73,78,93,128,148,179,184,188,193,197],"web":[28,43,102,157,198],"creates":[29],"problems":[30],"users":[32],"who":[33],"need":[34,67],"access":[36,71],"set":[38],"all":[40,72,147],"relevant":[42,74,129],"data":[44],"their":[46,96],"topics":[47],"interest.":[49],"Whether":[50],"you":[51,65],"are":[52],"fan":[54],"following":[55],"your":[56],"favorite":[57],"idol":[58],"or":[59,167,171],"journalist":[61],"investigating":[62],"may":[66],"not":[68],"only":[69],"information":[75],"but":[76],"also":[77],"recent":[79],"and":[81],"updates.":[82],"General":[83],"search":[84,158],"engines":[85],"like":[86],"Google":[87],"apply":[88],"several":[89],"techniques":[90,124],"enhance":[92],"freshness":[94],"crawled":[97],"data.":[98],"However,":[99],"in":[100,191],"focused":[101],"harvesting,":[103],"we":[104,121,139],"lack":[105],"an":[106],"efficient":[107],"approach":[108],"that":[109,125],"detects":[110],"topic":[115],"over":[116],"time.":[117],"paper,":[120],"focus":[122],"on":[123,196,206],"can":[126],"keep":[127],"query":[134,202],"up-to-date.":[135],"To":[136],"do":[137],"so,":[138],"test":[140],"four":[141],"different":[142],"approaches":[143,190],"efficiently":[145],"changed":[149,165,176,194],"documents":[150],"matching":[151],"entity":[154],"by":[155],"querying":[156],"engines.":[159],"We":[160],"define":[161],"document":[163,173],"with":[164,203],"newly":[169],"created":[170],"removed":[172],"as":[174],"document.":[177],"Among":[178],"proposed":[180],"change":[181],"detection":[182],"approaches,":[183],"FedWeb":[185],"method":[186],"outperforms":[187],"other":[189],"finding":[192],"20":[204],"percent,":[205],"average,":[207],"better":[208],"performance.":[209]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2016-09-23T00:00:00"}