{"id":"https://openalex.org/W2113136835","doi":"https://doi.org/10.1145/1531914.1531925","title":"Tag spam creates large non-giant connected components","display_name":"Tag spam creates large non-giant connected components","publication_year":2009,"publication_date":"2009-04-21","ids":{"openalex":"https://openalex.org/W2113136835","doi":"https://doi.org/10.1145/1531914.1531925","mag":"2113136835"},"language":"en","primary_location":{"id":"doi:10.1145/1531914.1531925","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th 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/A5022799931","display_name":"Nicolas Neubauer","orcid":"https://orcid.org/0009-0004-1456-0065"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicolas Neubauer","raw_affiliation_strings":["Technische Universit\u00e4t Berlin","Technische Universitat Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Technische Universitat Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066545155","display_name":"Robert Wetzker","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Wetzker","raw_affiliation_strings":["Technische Universit\u00e4t Berlin","Technische Universitat Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Technische Universitat Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103171859","display_name":"Klaus Obermayer","orcid":"https://orcid.org/0000-0002-5057-6142"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Obermayer","raw_affiliation_strings":["Technische Universit\u00e4t Berlin","Technische Universitat Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Technische Universitat Berlin","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3293,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91729595,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"52"},"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9976000189781189,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8278166055679321},{"id":"https://openalex.org/keywords/bookmarking","display_name":"Bookmarking","score":0.763343334197998},{"id":"https://openalex.org/keywords/connected-component","display_name":"Connected component","score":0.5349830985069275},{"id":"https://openalex.org/keywords/hypergraph","display_name":"Hypergraph","score":0.5231534242630005},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.4963586926460266},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48376893997192383},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47865164279937744},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4374101758003235},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3010441064834595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2429564893245697},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22842130064964294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10045695304870605},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.09782090783119202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278166055679321},{"id":"https://openalex.org/C176504155","wikidata":"https://www.wikidata.org/wiki/Q4943254","display_name":"Bookmarking","level":2,"score":0.763343334197998},{"id":"https://openalex.org/C193435613","wikidata":"https://www.wikidata.org/wiki/Q2997928","display_name":"Connected component","level":2,"score":0.5349830985069275},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.5231534242630005},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.4963586926460266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48376893997192383},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47865164279937744},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4374101758003235},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3010441064834595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2429564893245697},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22842130064964294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10045695304870605},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.09782090783119202},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1531914.1531925","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1986395638","https://openalex.org/W2009119083","https://openalex.org/W2080769514","https://openalex.org/W2127124926","https://openalex.org/W2340573765","https://openalex.org/W4241669766","https://openalex.org/W6793127252"],"related_works":["https://openalex.org/W2016627120","https://openalex.org/W2083130616","https://openalex.org/W70213055","https://openalex.org/W3025296469","https://openalex.org/W4233136760","https://openalex.org/W1978306220","https://openalex.org/W2546112266","https://openalex.org/W4225474873","https://openalex.org/W2521408379","https://openalex.org/W178077491"],"abstract_inverted_index":{"Spammers":[0],"in":[1,51,100,138],"social":[2],"bookmarking":[3,8],"systems":[4],"try":[5],"to":[6,13,44,58,92,107],"mimick":[7],"behaviour":[9],"of":[10,17,31,42,63,112,123],"real":[11],"users":[12,19,43,65,99],"gain":[14],"the":[15,29,101,110,113,120,124,131,141,158,170],"attention":[16],"other":[18],"or":[20,40],"search":[21],"engines.":[22],"Several":[23],"methods":[24],"have":[25],"been":[26],"proposed":[27,172],"for":[28],"detection":[30,164,186],"such":[32],"spam,":[33],"including":[34],"domain-specific":[35],"features":[36],"(like":[37],"URL":[38],"terms)":[39],"similarity":[41],"previously":[45],"identified":[46],"spammers.":[47],"However,":[48],"as":[49],"shown":[50],"our":[52,161],"previous":[53],"work,":[54],"it":[55],"is":[56,116,145],"possible":[57],"identify":[59],"a":[60],"large":[61],"fraction":[62],"spam":[64,98,163],"based":[66,165],"on":[67,166],"purely":[68],"structural":[69,167],"features.":[70],"The":[71],"hypergraph":[72,115],"connecting":[73],"documents,":[74],"users,":[75],"and":[76,84,127,180],"tags":[77],"can":[78,150],"be":[79,93,152],"decomposed":[80],"into":[81],"connected":[82],"components,":[83],"any":[85],"large,":[86],"but":[87],"non-giant":[88],"components":[89],"turned":[90],"out":[91],"almost":[94],"entirely":[95],"inhabitated":[96],"by":[97],"examined":[102],"dataset.":[103],"Here,":[104],"we":[105],"test":[106],"what":[108],"degree":[109],"decomposition":[111],"complete":[114],"really":[117],"necessary,":[118],"examining":[119],"component":[121],"structure":[122],"induced":[125],"user/document":[126,142],"user/tag":[128,132],"graphs.":[129],"While":[130],"graph's":[133,143],"connectivity":[134,144,155],"does":[135],"not":[136],"help":[137],"classifying":[139],"spammers,":[140],"already":[146],"highly":[147],"informative.":[148],"It":[149],"however":[151],"augmented":[153],"with":[154],"information":[156],"from":[157,178],"hypergraph.":[159],"In":[160],"view,":[162],"features,":[168],"like":[169],"one":[171],"here,":[173],"requires":[174],"complex":[175],"adaptation":[176],"strategies":[177],"spammers":[179],"may":[181],"complement":[182],"other,":[183],"more":[184],"traditional":[185],"approaches.":[187]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
