{"id":"https://openalex.org/W1575272122","doi":"https://doi.org/10.1007/978-3-642-17316-5_16","title":"Fixing the Threshold for Effective Detection of Near Duplicate Web Documents in Web Crawling","display_name":"Fixing the Threshold for Effective Detection of Near Duplicate Web Documents in Web Crawling","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1575272122","doi":"https://doi.org/10.1007/978-3-642-17316-5_16","mag":"1575272122"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-17316-5_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-17316-5_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5079351624","display_name":"V. A. Narayana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104573","display_name":"CMR University","ror":"https://ror.org/015waqy33","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210104573"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"V. A. Narayana","raw_affiliation_strings":["Department of Computer Science & Engineering, CMR College of Engineering & Technology, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, CMR College of Engineering & Technology, Hyderabad, India","institution_ids":["https://openalex.org/I4210104573"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107863294","display_name":"P. Premchand","orcid":null},"institutions":[{"id":"https://openalex.org/I8975392","display_name":"Osmania University","ror":"https://ror.org/030sjb889","country_code":"IN","type":"education","lineage":["https://openalex.org/I8975392"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P. Premchand","raw_affiliation_strings":["Department of Computer Science & Engineering, University College of Engineering, Osmania University, Hyderabad, AP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University College of Engineering, Osmania University, Hyderabad, AP, India","institution_ids":["https://openalex.org/I8975392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013033746","display_name":"A. Govardhan","orcid":"https://orcid.org/0000-0001-9239-0138"},"institutions":[{"id":"https://openalex.org/I10874241","display_name":"Jawaharlal Nehru Technological University, Hyderabad","ror":"https://ror.org/002tchr49","country_code":"IN","type":"education","lineage":["https://openalex.org/I10874241"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"A. Govardhan","raw_affiliation_strings":["JNTUH College of Engineering, Nachupally (Kondagattu), Karimnagar Dist, AP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JNTUH College of Engineering, Nachupally (Kondagattu), Karimnagar Dist, AP, India","institution_ids":["https://openalex.org/I10874241"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.5687,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85556916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9939000010490417,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9889000058174133,"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":0.7534158229827881},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7530680298805237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7130994200706482},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6793268322944641},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6384983062744141},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6057177186012268},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4549722671508789},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4340318441390991},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.42769619822502136},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.42019084095954895},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.22308635711669922},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07374024391174316}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7534158229827881},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7530680298805237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130994200706482},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6793268322944641},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6384983062744141},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6057177186012268},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4549722671508789},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4340318441390991},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.42769619822502136},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.42019084095954895},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.22308635711669922},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07374024391174316},{"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:10.1007/978-3-642-17316-5_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-17316-5_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W26591655","https://openalex.org/W1503924817","https://openalex.org/W1506845741","https://openalex.org/W1509577953","https://openalex.org/W1575770195","https://openalex.org/W1584848083","https://openalex.org/W1604983895","https://openalex.org/W1761577731","https://openalex.org/W1965704641","https://openalex.org/W1968155810","https://openalex.org/W2005677600","https://openalex.org/W2007842132","https://openalex.org/W2012833704","https://openalex.org/W2029341294","https://openalex.org/W2044434631","https://openalex.org/W2052253513","https://openalex.org/W2085922539","https://openalex.org/W2097184821","https://openalex.org/W2111549955","https://openalex.org/W2114353347","https://openalex.org/W2142211218","https://openalex.org/W2145349611","https://openalex.org/W2151932833","https://openalex.org/W2152565070","https://openalex.org/W2162502927","https://openalex.org/W2169189540","https://openalex.org/W2502247839","https://openalex.org/W2561675875","https://openalex.org/W3008251515","https://openalex.org/W3152156937"],"related_works":["https://openalex.org/W2056064491","https://openalex.org/W2379145789","https://openalex.org/W2772576376","https://openalex.org/W3022887243","https://openalex.org/W2311564458","https://openalex.org/W2113987729","https://openalex.org/W2380665498","https://openalex.org/W1981942450","https://openalex.org/W1575272122","https://openalex.org/W2548298479"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
