{"id":"https://openalex.org/W2049877827","doi":"https://doi.org/10.1145/1935826.1935886","title":"What blogs tell us about websites","display_name":"What blogs tell us about websites","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2049877827","doi":"https://doi.org/10.1145/1935826.1935886","mag":"2049877827"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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/A5039421197","display_name":"Matthew Michelson","orcid":"https://orcid.org/0000-0003-3346-2132"},"institutions":[{"id":"https://openalex.org/I2801840469","display_name":"Torch Technologies (United States)","ror":"https://ror.org/00nrhr905","country_code":"US","type":"company","lineage":["https://openalex.org/I2801840469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Michelson","raw_affiliation_strings":["Fetch Technologies, El Segundo, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fetch Technologies, El Segundo, CA, USA","institution_ids":["https://openalex.org/I2801840469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047798029","display_name":"Sofus A. Macskassy","orcid":null},"institutions":[{"id":"https://openalex.org/I2801840469","display_name":"Torch Technologies (United States)","ror":"https://ror.org/00nrhr905","country_code":"US","type":"company","lineage":["https://openalex.org/I2801840469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sofus A. Macskassy","raw_affiliation_strings":["Fetch Technologies, El Segundo, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fetch Technologies, El Segundo, CA, USA","institution_ids":["https://openalex.org/I2801840469"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2412,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57287237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"365","last_page":"374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9970999956130981,"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":0.9970999956130981,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9944000244140625,"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/T11644","display_name":"Spam and Phishing Detection","score":0.991100013256073,"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/demographics","display_name":"Demographics","score":0.94417804479599},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.6856841444969177},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.609756350517273},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5590493083000183},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.5472575426101685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5463117361068726},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5402851104736328},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47263118624687195},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.4542267322540283},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42758089303970337},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.15721175074577332},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.14071786403656006},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.10404244065284729},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08562487363815308},{"id":"https://openalex.org/keywords/demography","display_name":"Demography","score":0.08231091499328613}],"concepts":[{"id":"https://openalex.org/C2780084366","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demographics","level":2,"score":0.94417804479599},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.6856841444969177},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.609756350517273},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5590493083000183},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.5472575426101685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5463117361068726},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5402851104736328},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47263118624687195},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.4542267322540283},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42758089303970337},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.15721175074577332},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.14071786403656006},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10404244065284729},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08562487363815308},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.08231091499328613},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1935826.1935886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1537311738","https://openalex.org/W1815202964","https://openalex.org/W2005070837","https://openalex.org/W2012451152","https://openalex.org/W2063771604","https://openalex.org/W2065189722","https://openalex.org/W2072295764","https://openalex.org/W2078663894","https://openalex.org/W2102357195","https://openalex.org/W2110302976","https://openalex.org/W2130354913","https://openalex.org/W2133084001","https://openalex.org/W2135528482","https://openalex.org/W2145076066","https://openalex.org/W6676670208"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W2100945520","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W644339423","https://openalex.org/W2386525189","https://openalex.org/W2360284199"],"abstract_inverted_index":{"One":[0],"challenge":[1],"for":[2,129,142,159,173,183],"content":[3,121],"providers":[4],"on":[5,38,67],"the":[6,57,69,77,82,87,90,93,97,120,126,130,146,181],"Web":[7],"is":[8,22,59],"determining":[9,68,184],"who":[10,21,189],"consumes":[11],"their":[12,24],"content.":[13],"For":[14],"instance,":[15],"online":[16],"newspapers":[17],"want":[18],"to":[19,30,81,100,116,135,213],"know":[20],"reading":[23],"articles.":[25],"Previous":[26],"approaches":[27],"have":[28],"tried":[29],"determine":[31,101],"such":[32,103],"audience":[33,74],"demographics":[34,70,102,128,141,172],"by":[35,42,75],"placing":[36],"cookies":[37],"users'":[39],"systems,":[40],"or":[41,110],"directly":[43],"asking":[44],"consumers":[45],"(e.g.,":[46,186],"through":[47],"surveys).":[48],"The":[49],"first":[50],"approach":[51],"may":[52],"make":[53],"users":[54],"uncomfortable,":[55],"and":[56,92],"second":[58],"not":[60],"scalable.":[61],"In":[62,193],"this":[63,166],"paper":[64],"we":[65,155,179,196],"focus":[66],"of":[71,89,96,122,140,145],"a":[72,106,137,143,160,207],"Website's":[73,147],"analyzing":[76],"blogs":[78,91,198],"that":[79,151,169,211],"link":[80,212],"Website.":[83],"We":[84,149],"analyze":[85,197],"both":[86],"text":[88],"network":[94,99],"connectivity":[95],"blog":[98],"as":[104,178],"whether":[105],"person":[107],"\"is":[108],"married\"":[109],"\"has":[111],"pets.\"":[112],"Presumably":[113],"bloggers":[114,131,204],"linking":[115],"sites":[117,174],"also":[118],"consume":[119],"those":[123],"sites.":[124],"Therefore,":[125],"discovered":[127],"can":[132,156,175],"be":[133,176],"used":[134],"represent":[136],"proxy":[138],"set":[139],"subset":[144],"consumers.":[148],"demonstrate":[150],"in":[152],"many":[153],"cases":[154],"infer":[157],"sub-audiences":[158],"site":[161],"from":[162,200],"these":[163],"demographics.":[164],"Further,":[165],"feasibility":[167],"demonstrates":[168],"very":[170],"specific":[171],"generated":[177],"improve":[180],"methods":[182],"them":[185],"finding":[187],"people":[188],"play":[190],"video":[191],"games).":[192],"our":[194],"study":[195],"collected":[199,205],"more":[201,214],"than":[202,215],"590,000":[203],"over":[206],"six":[208],"month":[209],"period":[210],"488,000":[216],"distinct,":[217],"external":[218],"websites.":[219]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"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"}