{"id":"https://openalex.org/W1685426458","doi":"https://doi.org/10.1007/s10791-011-9162-z","title":"Efficient and effective spam filtering and re-ranking for large web datasets","display_name":"Efficient and effective spam filtering and re-ranking for large web datasets","publication_year":2011,"publication_date":"2011-01-29","ids":{"openalex":"https://openalex.org/W1685426458","doi":"https://doi.org/10.1007/s10791-011-9162-z","mag":"1685426458"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-011-9162-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10791-011-9162-z","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval","raw_type":"journal-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/A5084091807","display_name":"Gordon V. Cormack","orcid":"https://orcid.org/0000-0002-5890-0293"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Gordon V. Cormack","raw_affiliation_strings":["University of Waterloo, 200 University Avenue West, Waterloo, ON, N2L 3G1, Canada","University of Waterloo,Waterloo,Canada,N2L 3G1"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, 200 University Avenue West, Waterloo, ON, N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049222552","display_name":"Mark D. Smucker","orcid":"https://orcid.org/0000-0003-4968-6405"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mark D. Smucker","raw_affiliation_strings":["University of Waterloo, 200 University Avenue West, Waterloo, ON, N2L 3G1, Canada","University of Waterloo,Waterloo,Canada,N2L 3G1"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, 200 University Avenue West, Waterloo, ON, N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037737168","display_name":"Charles L. A. Clarke","orcid":"https://orcid.org/0000-0001-8178-9194"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Charles L. A. Clarke","raw_affiliation_strings":["University of Waterloo, 200 University Avenue West, Waterloo, ON, N2L 3G1, Canada","University of Waterloo,Waterloo,Canada,N2L 3G1"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, 200 University Avenue West, Waterloo, ON, N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo,Waterloo,Canada,N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084091807"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":96.4475,"has_fulltext":false,"cited_by_count":277,"citation_normalized_percentile":{"value":0.9995479,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"14","issue":"5","first_page":"441","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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/T11644","display_name":"Spam and Phishing Detection","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9987999796867371,"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":0.783906877040863},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7345713973045349},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.600544810295105},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.5331966280937195},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5216084718704224},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.496376097202301},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4508854150772095},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44709816575050354},{"id":"https://openalex.org/keywords/honeypot","display_name":"Honeypot","score":0.44327303767204285},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4327857196331024},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4264214336872101},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37205904722213745},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33788955211639404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23255088925361633},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.08207976818084717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07504871487617493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783906877040863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7345713973045349},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.600544810295105},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.5331966280937195},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5216084718704224},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.496376097202301},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4508854150772095},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44709816575050354},{"id":"https://openalex.org/C191267431","wikidata":"https://www.wikidata.org/wiki/Q911932","display_name":"Honeypot","level":2,"score":0.44327303767204285},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4327857196331024},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4264214336872101},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37205904722213745},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33788955211639404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23255088925361633},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.08207976818084717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07504871487617493},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10791-011-9162-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10791-011-9162-z","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W24701829","https://openalex.org/W94637519","https://openalex.org/W143775383","https://openalex.org/W157916489","https://openalex.org/W171854839","https://openalex.org/W176125184","https://openalex.org/W224439989","https://openalex.org/W569220443","https://openalex.org/W1516228069","https://openalex.org/W1518041103","https://openalex.org/W1571365592","https://openalex.org/W1601535310","https://openalex.org/W1606874436","https://openalex.org/W1767221188","https://openalex.org/W1974950122","https://openalex.org/W1988814344","https://openalex.org/W2004918107","https://openalex.org/W2008030886","https://openalex.org/W2009408190","https://openalex.org/W2021856948","https://openalex.org/W2066546027","https://openalex.org/W2089473834","https://openalex.org/W2119875355","https://openalex.org/W2121672615","https://openalex.org/W2124564482","https://openalex.org/W2246912952","https://openalex.org/W2398442511","https://openalex.org/W2399802085","https://openalex.org/W2916045930","https://openalex.org/W3013019162","https://openalex.org/W6603899496","https://openalex.org/W6605871289","https://openalex.org/W6606418737","https://openalex.org/W6607217061","https://openalex.org/W6634092990","https://openalex.org/W6636158958","https://openalex.org/W6675580205","https://openalex.org/W6691009775"],"related_works":["https://openalex.org/W2789663798","https://openalex.org/W2375896275","https://openalex.org/W2166943775","https://openalex.org/W1903420481","https://openalex.org/W2158007046","https://openalex.org/W2775236000","https://openalex.org/W2071426633","https://openalex.org/W4379381520","https://openalex.org/W1991531128","https://openalex.org/W2035739021"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":22},{"year":2015,"cited_by_count":21},{"year":2014,"cited_by_count":30},{"year":2013,"cited_by_count":36},{"year":2012,"cited_by_count":33}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
