{"id":"https://openalex.org/W2120721759","doi":"https://doi.org/10.1145/1135777.1135869","title":"Improved annotation of the blogosphere via autotagging and hierarchical clustering","display_name":"Improved annotation of the blogosphere via autotagging and hierarchical clustering","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2120721759","doi":"https://doi.org/10.1145/1135777.1135869","mag":"2120721759"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide 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/A5090224743","display_name":"Christopher Brooks","orcid":"https://orcid.org/0000-0003-2722-2730"},"institutions":[{"id":"https://openalex.org/I76766440","display_name":"University of San Francisco","ror":"https://ror.org/029m7xn54","country_code":"US","type":"education","lineage":["https://openalex.org/I76766440"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher H. Brooks","raw_affiliation_strings":["University of San Francisco, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"University of San Francisco, San Francisco, CA","institution_ids":["https://openalex.org/I76766440"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084182410","display_name":"Nancy Montanez","orcid":null},"institutions":[{"id":"https://openalex.org/I76766440","display_name":"University of San Francisco","ror":"https://ror.org/029m7xn54","country_code":"US","type":"education","lineage":["https://openalex.org/I76766440"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nancy Montanez","raw_affiliation_strings":["University of San Francisco, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"University of San Francisco, San Francisco, CA","institution_ids":["https://openalex.org/I76766440"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090224743"],"corresponding_institution_ids":["https://openalex.org/I76766440"],"apc_list":null,"apc_paid":null,"fwci":62.803,"has_fulltext":false,"cited_by_count":303,"citation_normalized_percentile":{"value":0.99943389,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"625","last_page":"632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9979000091552734,"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":0.864502489566803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8145790100097656},{"id":"https://openalex.org/keywords/folksonomy","display_name":"Folksonomy","score":0.8088929653167725},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7408104538917542},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6280269622802734},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6255784034729004},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5297254920005798},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5246958136558533},{"id":"https://openalex.org/keywords/tag-system","display_name":"Tag system","score":0.5067399144172668},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4750133454799652},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46708083152770996},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.44130146503448486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21943730115890503},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.16405031085014343}],"concepts":[{"id":"https://openalex.org/C2779661781","wikidata":"https://www.wikidata.org/wiki/Q374132","display_name":"Blogosphere","level":3,"score":0.864502489566803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145790100097656},{"id":"https://openalex.org/C2778431730","wikidata":"https://www.wikidata.org/wiki/Q494291","display_name":"Folksonomy","level":2,"score":0.8088929653167725},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7408104538917542},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6280269622802734},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6255784034729004},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5297254920005798},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5246958136558533},{"id":"https://openalex.org/C75003639","wikidata":"https://www.wikidata.org/wiki/Q3267583","display_name":"Tag system","level":2,"score":0.5067399144172668},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4750133454799652},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46708083152770996},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.44130146503448486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21943730115890503},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.16405031085014343},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1135777.1135869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.5132","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.5132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2006.org/programme/files/pdf/583.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1533946607","https://openalex.org/W1542417898","https://openalex.org/W1555563750","https://openalex.org/W1577231857","https://openalex.org/W1660390307","https://openalex.org/W1956559956","https://openalex.org/W1996764654","https://openalex.org/W2081580037","https://openalex.org/W2325227998","https://openalex.org/W4235968347","https://openalex.org/W4241122026","https://openalex.org/W6632118081","https://openalex.org/W6632440936","https://openalex.org/W6637101025","https://openalex.org/W6640862754"],"related_works":["https://openalex.org/W2154766759","https://openalex.org/W2143444208","https://openalex.org/W2909712102","https://openalex.org/W2092084389","https://openalex.org/W1950485419","https://openalex.org/W1971022461","https://openalex.org/W1978453817","https://openalex.org/W2622548874","https://openalex.org/W1577749430","https://openalex.org/W2028280063"],"abstract_inverted_index":{"Tags":[0],"have":[1],"recently":[2],"become":[3],"popular":[4],"as":[5,46],"a":[6,27,29,36,47,76,115,132],"means":[7],"of":[8,18,24,35,53,71,98,119,148],"annotating":[9],"and":[10,14,67,137],"organizing":[11],"Web":[12],"pages":[13],"blog":[15,57],"entries.":[16],"Advocates":[17],"tagging":[19,153],"argue":[20],"that":[21,74,80,104,124,139],"the":[22,33,44,51,61,69,95,149],"use":[23,42],"tags":[25,54,64,81],"produces":[26],"'folksonomy',":[28],"system":[30],"in":[31,93,151],"which":[32],"meaning":[34],"tag":[37],"is":[38],"determined":[39],"by":[40,59],"its":[41],"among":[43,135],"community":[45],"whole.":[48],"We":[49,78,101,121],"analyze":[50],"effectiveness":[52],"for":[55,84],"classifying":[56],"entries":[58],"gathering":[60],"top":[62],"350":[63],"from":[65],"Technorati":[66],"measuring":[68],"similarity":[70],"all":[72],"articles":[73,86],"share":[75],"tag.":[77],"find":[79],"are":[82],"useful":[83],"grouping":[85],"into":[87],"broad":[88],"categories,":[89],"but":[90],"less":[91],"effective":[92],"indicating":[94],"particular":[96],"content":[97],"an":[99],"article.":[100],"then":[102],"show":[103,123],"automatically":[105],"extracting":[106],"words":[107],"deemed":[108],"to":[109,130,145],"be":[110,128,143],"highly":[111],"relevant":[112],"can":[113,127],"produce":[114],"more":[116],"focused":[117],"categorization":[118],"articles.":[120],"also":[122],"clustering":[125],"algorithms":[126],"used":[129,144],"reconstruct":[131],"topical":[133],"hierarchy":[134],"tags,":[136],"suggest":[138],"these":[140],"approaches":[141],"may":[142],"address":[146],"some":[147],"weaknesses":[150],"current":[152],"systems.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":28}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
