{"id":"https://openalex.org/W2121308534","doi":"https://doi.org/10.1145/1244408.1244418","title":"Measuring similarity to detect qualified links","display_name":"Measuring similarity to detect qualified links","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2121308534","doi":"https://doi.org/10.1145/1244408.1244418","mag":"2121308534"},"language":"en","primary_location":{"id":"doi:10.1145/1244408.1244418","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244408.1244418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Adversarial information retrieval on the 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/A5024068814","display_name":"Xiaoguang Qi","orcid":"https://orcid.org/0000-0002-3465-9482"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaoguang Qi","raw_affiliation_strings":["Lehigh University","Lehigh University,"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]},{"raw_affiliation_string":"Lehigh University,","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067896271","display_name":"Lan Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan Nie","raw_affiliation_strings":["Lehigh University","Lehigh University,"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]},{"raw_affiliation_string":"Lehigh University,","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042328810","display_name":"Brian D. Davison","orcid":"https://orcid.org/0000-0002-9326-3648"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian D. Davison","raw_affiliation_strings":["Lehigh University","Lehigh University,"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]},{"raw_affiliation_string":"Lehigh University,","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024068814"],"corresponding_institution_ids":["https://openalex.org/I186143895"],"apc_list":null,"apc_paid":null,"fwci":3.3957,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93077849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9983999729156494,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9955999851226807,"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":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.760444164276123},{"id":"https://openalex.org/keywords/link-analysis","display_name":"Link analysis","score":0.6799066066741943},{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.5700202584266663},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.553214430809021},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.552923321723938},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.5253393054008484},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5195156335830688},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5109685659408569},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.507157564163208},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4542050063610077},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4401804208755493},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4154430031776428},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3489934802055359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3481130003929138},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2972816526889801},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.22251102328300476},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.15563246607780457},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11938118934631348},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.07499536871910095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760444164276123},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.6799066066741943},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.5700202584266663},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.553214430809021},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.552923321723938},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.5253393054008484},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5195156335830688},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5109685659408569},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.507157564163208},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4542050063610077},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4401804208755493},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4154430031776428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3489934802055359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3481130003929138},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2972816526889801},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.22251102328300476},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.15563246607780457},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11938118934631348},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.07499536871910095},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1244408.1244418","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244408.1244418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Adversarial information retrieval on the web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.352","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.lehigh.edu/~brian/pubs/2006/qualified-links/LU-CSE-06-033.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.84.7086","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.7086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://airweb.cse.lehigh.edu/2007/papers/paper_103.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1574862351","https://openalex.org/W1764421085","https://openalex.org/W1845137714","https://openalex.org/W1854214752","https://openalex.org/W1985554184","https://openalex.org/W1986831811","https://openalex.org/W1987365175","https://openalex.org/W1987389174","https://openalex.org/W2000333294","https://openalex.org/W2003471189","https://openalex.org/W2006119904","https://openalex.org/W2043900215","https://openalex.org/W2066055909","https://openalex.org/W2066636486","https://openalex.org/W2076470289","https://openalex.org/W2079672501","https://openalex.org/W2089199911","https://openalex.org/W2099324655","https://openalex.org/W2100815879","https://openalex.org/W2112400959","https://openalex.org/W2138621811","https://openalex.org/W2139148100","https://openalex.org/W2140204390","https://openalex.org/W2156632103","https://openalex.org/W4240407914","https://openalex.org/W4251560691","https://openalex.org/W6639055396","https://openalex.org/W6683392976"],"related_works":["https://openalex.org/W2380760159","https://openalex.org/W2305543783","https://openalex.org/W2963128065","https://openalex.org/W2583864867","https://openalex.org/W1598884124","https://openalex.org/W4248064238","https://openalex.org/W4254800508","https://openalex.org/W2018130068","https://openalex.org/W1999548128","https://openalex.org/W4254300012"],"abstract_inverted_index":{"The":[0,111],"early":[1],"success":[2],"of":[3,16,43,89,113,116,133,149],"link-based":[4],"ranking":[5],"algorithms":[6,103],"was":[7],"predicated":[8],"on":[9,106,158],"the":[10,17,41,80,87,107,131],"assumption":[11],"that":[12],"links":[13,23,33,73,94],"imply":[14],"merit":[15],"target":[18,84],"pages.":[19,85],"However,":[20],"today":[21],"many":[22],"exist":[24],"for":[25],"purposes":[26],"other":[27],"than":[28],"to":[29,47,56,70,145],"confer":[30],"authority.":[31],"Such":[32],"bring":[34],"noise":[35],"into":[36],"link":[37,101,109,159],"analysis":[38,102],"and":[39,59,83,97,136,139],"harm":[40],"quality":[42,50],"retrieval.":[44],"In":[45,63],"order":[46],"provide":[48],"high":[49],"search":[51],"results,":[52],"it":[53],"is":[54,68],"important":[55],"detect":[57,71],"them":[58],"reduce":[60],"their":[61],"influence.":[62],"this":[64],"paper,":[65],"a":[66,90,114,154],"method":[67],"proposed":[69],"such":[72],"by":[74,143],"considering":[75],"multiple":[76],"similarity":[77],"measures":[78],"over":[79],"source":[81],"pages":[82],"With":[86],"help":[88],"classifier,":[91],"these":[92],"noisy":[93],"are":[95,104,118],"detected":[96],"dropped.":[98],"After":[99],"that,":[100],"performed":[105],"reduced":[108],"graph.":[110],"usefulness":[112],"number":[115],"features":[117],"also":[119,152],"tested.":[120],"Experiments":[121],"across":[122],"53":[123],"query-specific":[124],"datasets":[125],"show":[126],"our":[127],"approach":[128,156],"almost":[129],"doubles":[130],"performance":[132],"Kleinberg's":[134],"HITS":[135],"boosts":[137],"Bharat":[138],"Henzinger's":[140],"imp":[141],"algorithm":[142],"close":[144],"9%":[146],"in":[147],"terms":[148],"precision.":[150],"It":[151],"outperforms":[153],"previous":[155],"focusing":[157],"farm":[160],"detection.":[161]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}