{"id":"https://openalex.org/W2117138276","doi":"https://doi.org/10.1007/s10994-010-5171-1","title":"Graph regularization methods for Web spam detection","display_name":"Graph regularization methods for Web spam detection","publication_year":2010,"publication_date":"2010-03-24","ids":{"openalex":"https://openalex.org/W2117138276","doi":"https://doi.org/10.1007/s10994-010-5171-1","mag":"2117138276"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-010-5171-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-010-5171-1","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-010-5171-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-010-5171-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021082077","display_name":"Jacob Abernethy","orcid":"https://orcid.org/0000-0002-3115-6804"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jacob Abernethy","raw_affiliation_strings":["University of California, Berkeley, USA","University of California\u2010Berkeley USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2010Berkeley USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075009867","display_name":"Olivier Chapelle","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Chapelle","raw_affiliation_strings":["Yahoo! Research, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084282503","display_name":"Carlos Castillo","orcid":"https://orcid.org/0000-0003-4544-0416"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Carlos Castillo","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain","Yahoo Res., Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo Res., Barcelona, Spain","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021082077"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":15.0114,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98749145,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"81","issue":"2","first_page":"207","last_page":"225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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/T11644","display_name":"Spam and Phishing Detection","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.816034197807312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912526726722717},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7511762380599976},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5854148268699646},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.500169038772583},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.45327699184417725},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4384395480155945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42311811447143555},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.4155002236366272},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4087860584259033},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38006147742271423},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32712167501449585},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3131788969039917},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.26741543412208557},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2620917558670044},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23542892932891846},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.13630229234695435},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12283667922019958}],"concepts":[{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.816034197807312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912526726722717},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7511762380599976},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5854148268699646},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.500169038772583},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.45327699184417725},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4384395480155945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42311811447143555},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.4155002236366272},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4087860584259033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38006147742271423},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32712167501449585},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3131788969039917},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.26741543412208557},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2620917558670044},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23542892932891846},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.13630229234695435},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12283667922019958},{"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/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10994-010-5171-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-010-5171-1","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-010-5171-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8307","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/%7Ejake/paper_webspam_mlj_final.pdf","raw_type":"text"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt8q0907wv","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/8q0907wv","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning, vol 81, iss 2","raw_type":"article"},{"id":"pmh:qt8q0907wv","is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/8q0907wv","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Abernethy, Jacob; Chapelle, Olivier; & Castillo, Carlos. (2010). Graph regularization methods for Web spam detection. Machine Learning, 81(2), pp 207-225. doi: 10.1007/s10994-010-5171-1. Retrieved from: http://www.escholarship.org/uc/item/8q0907wv","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10994-010-5171-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-010-5171-1","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-010-5171-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2117138276.pdf","grobid_xml":"https://content.openalex.org/works/W2117138276.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W106005634","https://openalex.org/W189202421","https://openalex.org/W1491300635","https://openalex.org/W1500474910","https://openalex.org/W1845137714","https://openalex.org/W1967825155","https://openalex.org/W1978705858","https://openalex.org/W1987365175","https://openalex.org/W2014134732","https://openalex.org/W2048679005","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2098841537","https://openalex.org/W2100081831","https://openalex.org/W2103456180","https://openalex.org/W2107428549","https://openalex.org/W2122505515","https://openalex.org/W2130196635","https://openalex.org/W2130854091","https://openalex.org/W2147898188","https://openalex.org/W2148603752","https://openalex.org/W2152814537","https://openalex.org/W2153277079","https://openalex.org/W2169270715","https://openalex.org/W2169470206","https://openalex.org/W2296319761","https://openalex.org/W2401383085","https://openalex.org/W2401715402","https://openalex.org/W4237640996","https://openalex.org/W4250589301","https://openalex.org/W4285719527","https://openalex.org/W6604315852","https://openalex.org/W6607569353","https://openalex.org/W6678180042","https://openalex.org/W6684893857","https://openalex.org/W6712761716","https://openalex.org/W6712844215","https://openalex.org/W7048191986","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W2098732437","https://openalex.org/W4776438","https://openalex.org/W2091208042","https://openalex.org/W2049541992","https://openalex.org/W2920666515","https://openalex.org/W2738482239","https://openalex.org/W2246912952","https://openalex.org/W1551975479","https://openalex.org/W2374596469","https://openalex.org/W2080521416"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"algorithm,":[3],"witch,":[4],"that":[5],"learns":[6],"to":[7],"detect":[8],"spam":[9,49],"hosts":[10],"or":[11],"pages":[12],"on":[13,45],"the":[14,23,26],"Web.":[15],"Unlike":[16],"most":[17],"other":[18],"approaches,":[19],"it":[20],"simultaneously":[21],"exploits":[22],"structure":[24],"of":[25],"Web":[27,48],"graph":[28],"as":[29,31],"well":[30],"page":[32],"contents":[33],"and":[34,41],"features.":[35],"The":[36],"method":[37],"is":[38],"efficient,":[39],"scalable,":[40],"provides":[42],"state-of-the-art":[43],"accuracy":[44],"a":[46],"standard":[47],"benchmark.":[50]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}