{"id":"https://openalex.org/W2026558262","doi":"https://doi.org/10.1145/1935826.1935905","title":"A probabilistic approach for learning folksonomies from structured data","display_name":"A probabilistic approach for learning folksonomies from structured data","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2026558262","doi":"https://doi.org/10.1145/1935826.1935905","mag":"2026558262"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935905","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/A5074458532","display_name":"Anon Plangprasopchok","orcid":"https://orcid.org/0000-0001-6659-580X"},"institutions":[{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Anon Plangprasopchok","raw_affiliation_strings":["National Electronics and Computer Technology Center Thailand, Pathumthani, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center Thailand, Pathumthani, Thailand","institution_ids":["https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049634383","display_name":"Kristina Lerman","orcid":"https://orcid.org/0000-0002-5071-0575"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristina Lerman","raw_affiliation_strings":["USC Information Sciences Institute, Marina del Rey, CA, USA"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina del Rey, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086169451","display_name":"Lise Getoor","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lise Getoor","raw_affiliation_strings":["University of Maryland, College Park, College Park, MD, USA","University of Maryland, College Park, College Park, MD, USA;"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, College Park, MD, USA;","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074458532"],"corresponding_institution_ids":["https://openalex.org/I14316845"],"apc_list":null,"apc_paid":null,"fwci":1.3029,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.78844807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"555","last_page":"564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9957000017166138,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9957000017166138,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9927999973297119,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7852997779846191},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6836309432983398},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6110642552375793},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5978385806083679},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5620443224906921},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5262355208396912},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.5255728363990784},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4843800961971283},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47672024369239807},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4514330327510834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42997485399246216},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4058968722820282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39183175563812256},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36530786752700806},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3004809021949768},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.1265033483505249},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.09483093023300171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852997779846191},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6836309432983398},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6110642552375793},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5978385806083679},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5620443224906921},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5262355208396912},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.5255728363990784},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4843800961971283},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47672024369239807},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4514330327510834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42997485399246216},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4058968722820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39183175563812256},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36530786752700806},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3004809021949768},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.1265033483505249},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.09483093023300171},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1935826.1935905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935905","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W1601600618","https://openalex.org/W1663973292","https://openalex.org/W1977970897","https://openalex.org/W2036216970","https://openalex.org/W2096166683","https://openalex.org/W2097266862","https://openalex.org/W2102775690","https://openalex.org/W2108836590","https://openalex.org/W2113979998","https://openalex.org/W2125149214","https://openalex.org/W2132827946","https://openalex.org/W2137813581","https://openalex.org/W2145500920","https://openalex.org/W2148019918","https://openalex.org/W2148727093","https://openalex.org/W2154331289","https://openalex.org/W2162723805","https://openalex.org/W2165232124","https://openalex.org/W2167699886","https://openalex.org/W2170112109","https://openalex.org/W2611894836","https://openalex.org/W4212863985","https://openalex.org/W6629510986","https://openalex.org/W6635963527","https://openalex.org/W6682564878","https://openalex.org/W6737354466"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W1976205134","https://openalex.org/W2381570729","https://openalex.org/W4248336175","https://openalex.org/W3009369890","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W4312490297","https://openalex.org/W2062212388"],"abstract_inverted_index":{"Learning":[0],"structured":[1],"representations":[2],"has":[3],"emerged":[4],"as":[5],"an":[6,43,130],"important":[7],"problem":[8],"in":[9],"many":[10,31,103],"domains,":[11],"including":[12],"document":[13],"and":[14,19,34,64,83,125],"Web":[15],"data":[16],"mining,":[17],"bioinformatics,":[18],"image":[20],"analysis.":[21],"One":[22],"approach":[23,46,89,119,131,141,150],"to":[24,29,52,122,129],"learning":[25],"complex":[26],"structures":[27,78],"is":[28,68,120],"integrate":[30],"smaller,":[32],"incomplete":[33],"noisy":[35],"structure":[36],"fragments.":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"present":[42],"unsupervised":[44],"probabilistic":[45],"that":[47,116],"extends":[48],"affinity":[49,136],"propagation":[50,137],"[7]":[51],"combine":[53],"the":[54,73,88,108,134,140],"small":[55],"ontological":[56],"fragments":[57],"into":[58],"a":[59,69,91,148],"collection":[60],"of":[61,97],"integrated,":[62],"consistent,":[63],"larger":[65],"folksonomies.":[66],"This":[67],"challenging":[70],"task":[71],"because":[72],"method":[74],"must":[75],"aggregate":[76],"similar":[77],"while":[79],"avoiding":[80],"structural":[81],"inconsistencies":[82],"handling":[84],"noise.":[85],"We":[86],"validate":[87],"on":[90,152],"real-world":[92],"social":[93],"media":[94],"dataset,":[95],"comprised":[96],"shallow":[98],"personal":[99],"hierarchies":[100],"specified":[101],"by":[102],"individual":[104],"users,":[105],"collected":[106],"from":[107],"photosharing":[109],"website":[110],"Flickr.":[111],"Our":[112],"empirical":[113],"results":[114],"show":[115],"our":[117],"proposed":[118],"able":[121],"construct":[123],"deeper":[124],"denser":[126],"structures,":[127],"compared":[128],"using":[132],"only":[133],"standard":[135],"algorithm.":[138],"Additionally,":[139],"yields":[142],"better":[143],"overall":[144],"integration":[145],"quality":[146],"than":[147],"state-of-the-art":[149],"based":[151],"incremental":[153],"relational":[154],"clustering.":[155]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}