{"id":"https://openalex.org/W2120516650","doi":"https://doi.org/10.1145/1531914.1531921","title":"An empirical study on selective sampling in active learning for splog detection","display_name":"An empirical study on selective sampling in active learning for splog detection","publication_year":2009,"publication_date":"2009-04-21","ids":{"openalex":"https://openalex.org/W2120516650","doi":"https://doi.org/10.1145/1531914.1531921","mag":"2120516650"},"language":"en","primary_location":{"id":"doi:10.1145/1531914.1531921","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531921","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/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/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/A5102880775","display_name":"Yuuki Sato","orcid":"https://orcid.org/0000-0002-4498-8490"},"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",", 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/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":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6238,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93258482,"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":"29","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9733999967575073,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.96670001745224,"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/support-vector-machine","display_name":"Support vector machine","score":0.763622522354126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7365862131118774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6509965658187866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6445439457893372},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6259426474571228},{"id":"https://openalex.org/keywords/hyperplane","display_name":"Hyperplane","score":0.6047523021697998},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.6046412587165833},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.553813099861145},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.45733386278152466},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.45127975940704346},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25580453872680664},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13620340824127197},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.10984602570533752},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10812857747077942}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.763622522354126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365862131118774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6509965658187866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6445439457893372},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6259426474571228},{"id":"https://openalex.org/C68693459","wikidata":"https://www.wikidata.org/wiki/Q657586","display_name":"Hyperplane","level":2,"score":0.6047523021697998},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.6046412587165833},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.553813099861145},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.45733386278152466},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.45127975940704346},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25580453872680664},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13620340824127197},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.10984602570533752},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10812857747077942},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1531914.1531921","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531921","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"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/W2085989833","https://openalex.org/W2107735203","https://openalex.org/W2120926619","https://openalex.org/W2146859361","https://openalex.org/W2156909104","https://openalex.org/W2159779194","https://openalex.org/W2169270715","https://openalex.org/W2185352626","https://openalex.org/W2318628205","https://openalex.org/W2401383085","https://openalex.org/W4285719527","https://openalex.org/W6606556609","https://openalex.org/W6686667547","https://openalex.org/W6712844215"],"related_works":["https://openalex.org/W2369655046","https://openalex.org/W2019467317","https://openalex.org/W2161440356","https://openalex.org/W2383335574","https://openalex.org/W1489507320","https://openalex.org/W1889103747","https://openalex.org/W2348510359","https://openalex.org/W3121830895","https://openalex.org/W2900686919","https://openalex.org/W2047800684"],"abstract_inverted_index":{"This":[0],"paper":[1,46],"studies":[2],"how":[3],"to":[4,77,99],"reduce":[5],"the":[6,18,30,37,71,74,104,118],"amount":[7],"of":[8,20,39,66,95,106,112],"human":[9],"supervision":[10],"for":[11,51,89],"identifying":[12],"splogs":[13],"/":[14,41,108],"authentic":[15,42,109],"blogs":[16],"in":[17,54,86,103],"context":[19],"continuously":[21],"updating":[22],"splog":[23,40,107],"data":[24],"sets":[25],"year":[26],"by":[27,57],"year.":[28],"Following":[29],"previous":[31],"works":[32],"on":[33],"active":[34,55,87,97],"learning,":[35,68],"against":[36],"task":[38,105],"blog":[43,110],"detection,":[44],"this":[45,113],"empirically":[47],"examines":[48],"several":[49],"strategies":[50],"selective":[52],"sampling":[53],"learning":[56,88,98],"Support":[58],"Vector":[59],"Machines":[60],"(SVMs).":[61],"As":[62],"a":[63],"confidence":[64],"measure":[65],"SVMs":[67],"we":[69],"employ":[70],"distance":[72],"from":[73],"separating":[75],"hyperplane":[76],"each":[78],"test":[79],"instance,":[80],"which":[81],"have":[82],"been":[83],"well":[84],"studied":[85],"text":[90,100],"classification.":[91],"Unlike":[92],"those":[93],"results":[94],"applying":[96],"classification":[101],"tasks,":[102],"detection":[111],"paper,":[114],"it":[115],"is":[116],"not":[117],"case":[119],"that":[120],"adding":[121],"least":[122],"confident":[123],"samples":[124],"peforms":[125],"best.":[126]},"counts_by_year":[{"year":2017,"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"}