{"id":"https://openalex.org/W2066055909","doi":"https://doi.org/10.1145/1135777.1135794","title":"Detecting spam web pages through content analysis","display_name":"Detecting spam web pages through content analysis","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2066055909","doi":"https://doi.org/10.1145/1135777.1135794","mag":"2066055909"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-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/A5030400740","display_name":"Alexandros Ntoulas","orcid":null},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"funder","lineage":["https://openalex.org/I2799798094"]},{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexandros Ntoulas","raw_affiliation_strings":["UCLA Computer Science Dept., Los Angeles, CA","UCLA Computer Science Department, Los Angeles CA"],"affiliations":[{"raw_affiliation_string":"UCLA Computer Science Dept., Los Angeles, CA","institution_ids":["https://openalex.org/I2799798094"]},{"raw_affiliation_string":"UCLA Computer Science Department, Los Angeles CA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037200145","display_name":"Marc Najork","orcid":"https://orcid.org/0000-0003-1423-0854"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Najork","raw_affiliation_strings":["Microsoft Research, Mountain View, CA","[Microsoft Research, Mountain View, CA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research, Mountain View, CA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015555842","display_name":"Mark S. Manasse","orcid":"https://orcid.org/0000-0002-8981-8225"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Manasse","raw_affiliation_strings":["Microsoft Research, Mountain View, CA","[Microsoft Research, Mountain View, CA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research, Mountain View, CA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060832606","display_name":"Dennis Fetterly","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Fetterly","raw_affiliation_strings":["Microsoft Research, Mountain View, CA","[Microsoft Research, Mountain View, CA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research, Mountain View, CA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030400740"],"corresponding_institution_ids":["https://openalex.org/I161318765","https://openalex.org/I2799798094"],"apc_list":null,"apc_paid":null,"fwci":113.7668,"has_fulltext":false,"cited_by_count":615,"citation_normalized_percentile":{"value":0.99977041,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"92"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.998199999332428,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.7700016498565674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7157230973243713},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7139197587966919},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6008856892585754},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5864770412445068},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.57569420337677},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.5312734842300415},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5081229209899902},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.43045663833618164},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.4153568744659424},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.29235512018203735},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.22203904390335083},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.15098515152931213}],"concepts":[{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.7700016498565674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157230973243713},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7139197587966919},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6008856892585754},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5864770412445068},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.57569420337677},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.5312734842300415},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5081229209899902},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.43045663833618164},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.4153568744659424},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.29235512018203735},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.22203904390335083},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.15098515152931213},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1135777.1135794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.387.3479","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.387.3479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.wellesley.edu/~cs315/Papers/Ntoulas-DetectingSpamThroughContentAnalysis.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.897","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/research/sv/sv-pubs/www2006.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W449364","https://openalex.org/W38924359","https://openalex.org/W49362422","https://openalex.org/W202878612","https://openalex.org/W1574901103","https://openalex.org/W1648885110","https://openalex.org/W1764421085","https://openalex.org/W1845137714","https://openalex.org/W1854214752","https://openalex.org/W1966280301","https://openalex.org/W1967825155","https://openalex.org/W1987365175","https://openalex.org/W1988790447","https://openalex.org/W2050028965","https://openalex.org/W2099324655","https://openalex.org/W2108313281","https://openalex.org/W2108671511","https://openalex.org/W2113417702","https://openalex.org/W2125055259","https://openalex.org/W2128272588","https://openalex.org/W2139148100","https://openalex.org/W2149397822","https://openalex.org/W2156632103","https://openalex.org/W2169270715","https://openalex.org/W2401383085","https://openalex.org/W2912934387"],"related_works":["https://openalex.org/W2080521416","https://openalex.org/W2091208042","https://openalex.org/W2018000323","https://openalex.org/W2920666515","https://openalex.org/W2738482239","https://openalex.org/W2246912952","https://openalex.org/W2552201931","https://openalex.org/W1551975479","https://openalex.org/W3098355271","https://openalex.org/W2100081831"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"continue":[4],"our":[5,64,77],"investigations":[6],"of":[7,12,51,70,80],"\"web":[8],"spam\":":[9],"the":[10,16,22,49,71],"injection":[11],"artificially-created":[13],"pages":[14,32,74,89],"into":[15],"web":[17],"in":[18,54,76],"order":[19],"to":[20,27,30],"influence":[21],"results":[23],"from":[24],"search":[25],"engines,":[26],"drive":[28],"traffic":[29],"certain":[31],"for":[33,43],"fun":[34],"or":[35],"profit.":[36],"This":[37],"paper":[38],"considers":[39],"some":[40],"previously-undescribed":[41],"techniques":[42,53],"automatically":[44],"detecting":[45],"spam":[46,73,86],"pages,":[47,82],"examines":[48],"effectiveness":[50],"these":[52],"isolation":[55],"and":[56,87],"when":[57],"aggregated":[58],"using":[59],"classification":[60],"algorithms.":[61],"When":[62],"combined,":[63],"heuristics":[65],"correctly":[66],"identify":[67],"2,037":[68],"(86.2%)":[69],"2,364":[72],"(13.8%)":[75],"judged":[78],"collection":[79],"17,168":[81],"while":[83],"misidentifying":[84],"526":[85],"non-spam":[88],"(3.1%).":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":38},{"year":2016,"cited_by_count":38},{"year":2015,"cited_by_count":42},{"year":2014,"cited_by_count":42},{"year":2013,"cited_by_count":55},{"year":2012,"cited_by_count":54}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
