{"id":"https://openalex.org/W2159779194","doi":"https://doi.org/10.1145/1451983.1451993","title":"Analysing features of Japanese splogs and characteristics of keywords","display_name":"Analysing features of Japanese splogs and characteristics of keywords","publication_year":2008,"publication_date":"2008-04-22","ids":{"openalex":"https://openalex.org/W2159779194","doi":"https://doi.org/10.1145/1451983.1451993","mag":"2159779194"},"language":"en","primary_location":{"id":"doi:10.1145/1451983.1451993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1451983.1451993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th 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/A5110389332","display_name":"Yuuki Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuuki Sato","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066456246","display_name":"Takehito Utsuro","orcid":"https://orcid.org/0000-0003-4072-1833"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takehito Utsuro","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105938656","display_name":"Yoshiaki Murakami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshiaki Murakami","raw_affiliation_strings":["Navix Co., Ltd., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navix Co., Ltd., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109064855","display_name":"Tomohiro Fukuhara","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Fukuhara","raw_affiliation_strings":["University of Tokyo, Kashiwa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Kashiwa, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020912760","display_name":"Hiroshi Nakagawa","orcid":"https://orcid.org/0000-0002-3024-9136"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Nakagawa","raw_affiliation_strings":["University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110632437","display_name":"Yasuhide Kawada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasuhide Kawada","raw_affiliation_strings":["Navix Co., Ltd., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navix Co., Ltd., Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045875579","display_name":"Noriko Kando","orcid":"https://orcid.org/0000-0002-2133-0215"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noriko Kando","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.757,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.97463964,"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":"33","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980999827384949,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9968000054359436,"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/blogosphere","display_name":"Blogosphere","score":0.9139225482940674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412670850753784},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4896584153175354},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4782094955444336},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4675793945789337},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4435498118400574},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.11979565024375916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07496270537376404},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.070200115442276}],"concepts":[{"id":"https://openalex.org/C2779661781","wikidata":"https://www.wikidata.org/wiki/Q374132","display_name":"Blogosphere","level":3,"score":0.9139225482940674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412670850753784},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4896584153175354},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4782094955444336},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4675793945789337},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4435498118400574},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.11979565024375916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07496270537376404},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.070200115442276},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1451983.1451993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1451983.1451993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th international workshop on Adversarial information retrieval on the web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.93","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.93","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/2008/submissions/sato_2008_japan_splog_characterization.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.506.993","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.506.993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.iit.tsukuba.ac.jp/member/utsuro/research/papers/utsuro/main-airweb2008-final-embedded-A4.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.588.7223","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.588.7223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.r.dl.itc.u-tokyo.ac.jp/~nakagawa/academic-res/airweb2008-utsuro.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":17,"referenced_works":["https://openalex.org/W103280473","https://openalex.org/W160659377","https://openalex.org/W172410088","https://openalex.org/W1977733111","https://openalex.org/W2107735203","https://openalex.org/W2120926619","https://openalex.org/W2137122695","https://openalex.org/W2146859361","https://openalex.org/W2169270715","https://openalex.org/W2169470206","https://openalex.org/W2183221394","https://openalex.org/W2185352626","https://openalex.org/W2482297295","https://openalex.org/W4285719527","https://openalex.org/W6606556609","https://openalex.org/W6684893857","https://openalex.org/W6686667547"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2170860410","https://openalex.org/W2992958761","https://openalex.org/W3162250950","https://openalex.org/W2406269149","https://openalex.org/W2183591868","https://openalex.org/W4394774866","https://openalex.org/W38658537","https://openalex.org/W4312070466","https://openalex.org/W3209989275"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,8,68],"analyzing":[4,29],"(Japanese)":[5],"splogs":[6,24,38,57,127],"based":[7],"various":[9,79,112],"characteristics":[10,31],"of":[11,20,32,64,81,124,135],"keywords":[12,33,63],"contained":[13,34],"in":[14,35,42,46],"them.":[15],"We":[16,76],"estimate":[17],"the":[18,30,47,69,125],"behavior":[19],"spammers":[21],"when":[22],"creating":[23],"from":[25,92],"other":[26,93],"sources":[27,94],"by":[28,58,130],"splogs.":[36],"Since":[37],"often":[39],"cause":[40],"noises":[41],"word":[43],"occurrence":[44],"statistics":[45],"blogosphere,":[48],"we":[49,52],"assume":[50],"that":[51,120],"can":[53],"efficiently":[54],"(manually)":[55],"collect":[56],"sampling":[59],"blog":[60,83],"homepages":[61,84],"containing":[62],"a":[65,131],"certain":[66],"type":[67],"date":[70],"with":[71],"its":[72],"most":[73],"frequent":[74],"occurrence.":[75],"manually":[77],"examine":[78],"features":[80],"collected":[82,126],"regarding":[85],"whether":[86,100],"their":[87],"text":[88],"content":[89],"is":[90,116],"excerpt":[91],"or":[95,105],"not,":[96],"as":[97,99],"well":[98],"they":[101],"display":[102],"affiliate":[103],"advertisement":[104],"out-going":[106],"links":[107],"to":[108,118],"affiliated":[109],"sites.":[110],"Among":[111],"informative":[113],"results,":[114],"it":[115],"important":[117],"note":[119],"more":[121],"than":[122],"half":[123],"are":[128],"created":[129],"very":[132],"small":[133],"number":[134],"spammers.":[136]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
