{"id":"https://openalex.org/W2107473756","doi":"https://doi.org/10.1145/2467696.2467706","title":"Automatic tag recommendation for metadata annotation using probabilistic topic modeling","display_name":"Automatic tag recommendation for metadata annotation using probabilistic topic modeling","publication_year":2013,"publication_date":"2013-07-22","ids":{"openalex":"https://openalex.org/W2107473756","doi":"https://doi.org/10.1145/2467696.2467706","mag":"2107473756"},"language":"en","primary_location":{"id":"doi:10.1145/2467696.2467706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2467696.2467706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries","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/A5023506216","display_name":"Suppawong Tuarob","orcid":"https://orcid.org/0000-0002-5201-5699"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Suppawong Tuarob","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044729983","display_name":"Line Pouchard","orcid":"https://orcid.org/0000-0002-2120-6521"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Line C. Pouchard","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023506216"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":19.2359,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.99305681,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9900000095367432,"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/metadata","display_name":"Metadata","score":0.9256502985954285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8056726455688477},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7004609704017639},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6747704148292542},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.4522760510444641},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.4430800676345825},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43063902854919434},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41337376832962036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1170138418674469}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9256502985954285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8056726455688477},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7004609704017639},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6747704148292542},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.4522760510444641},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.4430800676345825},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43063902854919434},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41337376832962036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1170138418674469}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2467696.2467706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2467696.2467706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W121380867","https://openalex.org/W1532325895","https://openalex.org/W1590650811","https://openalex.org/W1880262756","https://openalex.org/W1980397870","https://openalex.org/W2031237011","https://openalex.org/W2051093690","https://openalex.org/W2060772621","https://openalex.org/W2086511124","https://openalex.org/W2090041477","https://openalex.org/W2100802943","https://openalex.org/W2109244020","https://openalex.org/W2110642088","https://openalex.org/W2116926073","https://openalex.org/W2122778642","https://openalex.org/W2123107811","https://openalex.org/W2124998943","https://openalex.org/W2150032155","https://openalex.org/W2161353674","https://openalex.org/W2161846127","https://openalex.org/W2162107206","https://openalex.org/W2163659824","https://openalex.org/W2173213060","https://openalex.org/W2179804212","https://openalex.org/W2341904430","https://openalex.org/W6672077861"],"related_works":["https://openalex.org/W3084772717","https://openalex.org/W1773645839","https://openalex.org/W2380261968","https://openalex.org/W2907247951","https://openalex.org/W3122624872","https://openalex.org/W3198863654","https://openalex.org/W2136226335","https://openalex.org/W2796209520","https://openalex.org/W2018424284","https://openalex.org/W2366936177"],"abstract_inverted_index":{"The":[0],"increase":[1],"of":[2,46,79,135,155,166,179,190],"the":[3,15,44,47,52,80,95,101,139,177,187,191],"complexity":[4],"and":[5,9,24,91,107,151],"advancement":[6],"in":[7,39,43],"ecological":[8],"environmental":[10,90,167],"sciences":[11],"encourages":[12],"scientists":[13,60],"across":[14,94],"world":[16],"to":[17,27,63,83],"collect":[18],"data":[19,35,48,93,102],"from":[20,100],"multiple":[21,105],"places,":[22],"times,":[23],"thematic":[25],"scales":[26],"verify":[28],"their":[29],"hypotheses.":[30],"Accumulated":[31],"over":[32],"time,":[33],"such":[34,70],"not":[36,171],"only":[37,172],"increases":[38],"amount,":[40],"but":[41,182],"also":[42,183],"diversity":[45],"sources":[49],"spread":[50],"around":[51],"world.":[53],"This":[54],"poses":[55],"a":[56,86,142,147],"huge":[57],"challenge":[58],"for":[59,66,88,132,158],"who":[61],"have":[62],"manually":[64],"search":[65],"information.":[67],"To":[68],"alleviate":[69],"problems,":[71],"ONEMercury":[72,97],"has":[73],"recently":[74],"been":[75],"implemented":[76],"as":[77,85],"part":[78],"DataONE":[81],"project":[82],"serve":[84],"portal":[87],"accessing":[89],"observational":[92],"globe.":[96],"harvests":[98],"metadata":[99,113,169],"hosted":[103],"by":[104],"repositories":[106],"makes":[108],"it":[109],"searchable.":[110],"However,":[111],"harvested":[112],"records":[114,170],"sometimes":[115],"are":[116],"poorly":[117],"annotated":[118],"or":[119],"lacking":[120],"meaningful":[121],"keywords,":[122],"which":[123],"could":[124],"affect":[125],"effective":[126],"retrieval.":[127],"Here,":[128],"we":[129],"develop":[130],"algorithms":[131],"automatic":[133],"annotation":[134],"metadata.":[136],"We":[137],"transform":[138],"problem":[140,145],"into":[141],"tag":[143,149],"recommendation":[144],"with":[146],"controlled":[148],"library,":[150],"propose":[152],"two":[153],"variants":[154],"an":[156],"algorithm":[157],"recommending":[159],"tags.":[160],"Our":[161],"experiments":[162],"on":[163,176,186],"four":[164],"datasets":[165],"science":[168],"show":[173],"great":[174],"promises":[175],"performance":[178],"our":[180],"method,":[181],"shed":[184],"light":[185],"different":[188],"natures":[189],"datasets.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}