{"id":"https://openalex.org/W1997805268","doi":"https://doi.org/10.1145/2108616.2108661","title":"Detecting splogs using similarities of splog HTML structures","display_name":"Detecting splogs using similarities of splog HTML structures","publication_year":2010,"publication_date":"2010-01-14","ids":{"openalex":"https://openalex.org/W1997805268","doi":"https://doi.org/10.1145/2108616.2108661","mag":"1997805268"},"language":"en","primary_location":{"id":"doi:10.1145/2108616.2108661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2108616.2108661","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 Conference on Uniquitous Information Management and Communication","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/A5017624929","display_name":"Taichi Katayama","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":"Taichi Katayama","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan",", University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":", University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020758911","display_name":"Takayuki Yoshinaka","orcid":null},"institutions":[{"id":"https://openalex.org/I165522056","display_name":"Tokyo Denki University","ror":"https://ror.org/01pa62v70","country_code":"JP","type":"education","lineage":["https://openalex.org/I165522056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Yoshinaka","raw_affiliation_strings":["Tokyo Denki University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Denki University, Tokyo, Japan","institution_ids":["https://openalex.org/I165522056"]}]},{"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",", University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":", University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"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/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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88015816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/spamming","display_name":"Spamming","score":0.9791446328163147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7290410995483398},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5853714942932129},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.426624596118927},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34854555130004883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33908307552337646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17377319931983948},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.164711594581604},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1301632523536682}],"concepts":[{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.9791446328163147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290410995483398},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5853714942932129},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.426624596118927},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34854555130004883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33908307552337646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17377319931983948},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.164711594581604},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1301632523536682}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2108616.2108661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2108616.2108661","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 Conference on Uniquitous Information Management and Communication","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":26,"referenced_works":["https://openalex.org/W160659377","https://openalex.org/W172410088","https://openalex.org/W1514940655","https://openalex.org/W1515450954","https://openalex.org/W1977733111","https://openalex.org/W2019264297","https://openalex.org/W2085989833","https://openalex.org/W2102619140","https://openalex.org/W2107735203","https://openalex.org/W2120516650","https://openalex.org/W2120926619","https://openalex.org/W2146486820","https://openalex.org/W2146859361","https://openalex.org/W2148603752","https://openalex.org/W2159779194","https://openalex.org/W2169270715","https://openalex.org/W2169470206","https://openalex.org/W2185352626","https://openalex.org/W2401383085","https://openalex.org/W4285719527","https://openalex.org/W6606556609","https://openalex.org/W6675258595","https://openalex.org/W6684893857","https://openalex.org/W6686667547","https://openalex.org/W6712844215","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1987732684","https://openalex.org/W2286465138","https://openalex.org/W637393809","https://openalex.org/W2808742736","https://openalex.org/W1526983901","https://openalex.org/W3126526144","https://openalex.org/W3021299372","https://openalex.org/W2184211279","https://openalex.org/W2346278349"],"abstract_inverted_index":{"Spam":[0],"blogs":[1,5],"or":[2,13,23],"splogs":[3,43,64,109],"are":[4,45],"hosting":[6,21],"spam":[7],"posts,":[8],"created":[9,49,65,113],"using":[10],"machine":[11],"generated":[12],"hijacked":[14],"content":[15],"for":[16],"the":[17,25,73,95,105],"sole":[18],"purpose":[19],"of":[20,27,29,42,59,75,81,88,92,98,108],"advertisements":[22],"increasing":[24],"number":[26],"inlinks":[28],"target":[30],"sites.":[31],"Among":[32],"those":[33,63],"splogs,":[34],"this":[35,125],"paper":[36],"focuses":[37],"on":[38],"detecting":[39],"a":[40,86,99],"group":[41],"which":[44],"estimated":[46,110],"to":[47,71,111,119],"be":[48,112],"by":[50,66,114],"an":[51,67,115],"identical":[52,68,116],"spammer.":[53],"We":[54,102],"especially":[55],"show":[56,103],"that":[57,104],"similarities":[58,80],"html":[60,82,100,106],"structures":[61],"among":[62],"spammer":[69,117],"contribute":[70],"improving":[72],"performance":[74],"splog":[76,131],"detection.":[77,132],"In":[78],"measuring":[79],"structures,":[83],"we":[84],"extract":[85],"list":[87],"blocks":[89],"(minimum":[90],"unit":[91],"content)":[93],"from":[94],"DOM":[96,122],"tree":[97],"file.":[101],"files":[107],"tend":[118],"have":[120],"similar":[121],"trees":[123],"and":[124],"tendency":[126],"is":[127],"quite":[128],"effective":[129],"in":[130]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
