{"id":"https://openalex.org/W1976974489","doi":"https://doi.org/10.1145/1774088.1774269","title":"Host-IP clustering technique for deep web characterization","display_name":"Host-IP clustering technique for deep web characterization","publication_year":2010,"publication_date":"2010-03-22","ids":{"openalex":"https://openalex.org/W1976974489","doi":"https://doi.org/10.1145/1774088.1774269","mag":"1976974489"},"language":"en","primary_location":{"id":"doi:10.1145/1774088.1774269","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774269","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":"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/A5103329268","display_name":"Denis Shestakov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denis Shestakov","raw_affiliation_strings":["Helsinki University of Technology, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology, Finland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105839982","display_name":"Tapio Salakoski","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tapio Salakoski","raw_affiliation_strings":["University of Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2188,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.46071189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"874","last_page":"875"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13976","display_name":"Web visibility and informetrics","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.7828646898269653},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5412217974662781},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5295529961585999},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.5067620873451233},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.48976993560791016},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4895978569984436},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.46943286061286926},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4676598608493805},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.46189701557159424},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.44527560472488403},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.44515475630760193},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.44472751021385193},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37226027250289917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2600265145301819},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1188497543334961},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.06305873394012451}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828646898269653},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5412217974662781},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5295529961585999},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5067620873451233},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.48976993560791016},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4895978569984436},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.46943286061286926},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4676598608493805},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.46189701557159424},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.44527560472488403},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.44515475630760193},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.44472751021385193},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37226027250289917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2600265145301819},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1188497543334961},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.06305873394012451},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1774088.1774269","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774269","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":[{"score":0.5,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1498286998","https://openalex.org/W1570649210","https://openalex.org/W1999478104","https://openalex.org/W2013970953","https://openalex.org/W2094930182","https://openalex.org/W2125969310"],"related_works":["https://openalex.org/W2366747481","https://openalex.org/W3136060338","https://openalex.org/W2379065217","https://openalex.org/W2064912272","https://openalex.org/W2035629744","https://openalex.org/W4300567571","https://openalex.org/W2365708522","https://openalex.org/W2123742265","https://openalex.org/W1850871278","https://openalex.org/W2182622516"],"abstract_inverted_index":{"The":[0],"part":[1],"of":[2,22,41,44,64,80],"the":[3,7,26,45,56,69,78,105],"Web,":[4,9],"known":[5],"as":[6,20],"deep":[8,46,70,106],"is":[10,28],"to":[11,67,101],"date":[12],"relatively":[13],"unexplored":[14],"and":[15,72],"even":[16],"major":[17],"characteristics":[18],"such":[19],"number":[21],"searchable":[23],"databases":[24],"on":[25,77],"Web":[27,47,71,82],"somewhat":[29],"disputable.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"are":[35],"aimed":[36],"at":[37],"more":[38],"accurate":[39],"estimation":[40],"main":[42],"parameters":[43],"by":[48],"sampling":[49,59,93],"one":[50],"national":[51],"web":[52],"domain.":[53],"We":[54],"propose":[55],"Host-IP":[57],"clustering":[58],"technique":[60],"that":[61],"addresses":[62],"drawbacks":[63],"existing":[65],"approaches":[66],"characterize":[68],"report":[73],"our":[74],"findings":[75],"based":[76],"survey":[79],"Russian":[81],"conducted":[83],"in":[84,104],"September":[85],"2006.":[86],"Obtained":[87],"estimates":[88],"together":[89],"with":[90],"a":[91],"proposed":[92],"method":[94],"could":[95],"be":[96],"useful":[97],"for":[98],"further":[99],"studies":[100],"handle":[102],"data":[103],"Web.":[107]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
