{"id":"https://openalex.org/W6945723266","doi":"https://doi.org/10.26190/unsworks/15971","title":"Integrating community knowledge acquisition and data features analysis for recommending entity similarity functions","display_name":"Integrating community knowledge acquisition and data features analysis for recommending entity similarity functions","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W6945723266","doi":"https://doi.org/10.26190/unsworks/15971"},"language":"en","primary_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/52436","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.4/52436","pdf_url":null,"source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.26190/unsworks/15971","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ryu, Seung Hwan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ryu, Seung Hwan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.24300000071525574,"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/T10028","display_name":"Topic Modeling","score":0.24300000071525574,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.18539999425411224,"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/T11719","display_name":"Data Quality and Management","score":0.06210000067949295,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7649999856948853},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.7547000050544739},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5924000144004822},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5605000257492065},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4632999897003174},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4474000036716461},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.3873000144958496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860000133514404},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7649999856948853},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.7547000050544739},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5856000185012817},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37790000438690186},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/52436","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.4/52436","pdf_url":null,"source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},{"id":"doi:10.26190/unsworks/15971","is_oa":true,"landing_page_url":"https://doi.org/10.26190/unsworks/15971","pdf_url":null,"source":{"id":"https://openalex.org/S7407053176","display_name":"University of New South Wales","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.26190/unsworks/15971","is_oa":true,"landing_page_url":"https://doi.org/10.26190/unsworks/15971","pdf_url":null,"source":{"id":"https://openalex.org/S7407053176","display_name":"University of New South Wales","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Similar":[0],"entity":[1,15,26,153,193,240],"search":[2,27,87],"is":[3,94,99],"the":[4,64,72,77,90,97,127,210,248],"task":[5,98],"of":[6,74,76,252],"identifying":[7],"entities":[8,234],"that":[9],"most":[10,81],"closely":[11],"resemble":[12],"a":[13,17,19,29,84,237],"given":[14,85,238],"(e.g.,":[16,116,152,187],"person,":[18],"document,":[20],"or":[21,119,169,180,189],"an":[22,109,135],"image).":[23],"The":[24,132],"similar":[25,235],"plays":[28],"vital":[30],"role":[31],"in":[32,46,63,232],"many":[33,55],"application":[34],"domains":[35],"such":[36],"as":[37,96],"product":[38],"search,":[39,41,43],"people":[40],"document":[42],"data":[44,185],"integration":[45],"business":[47],"intelligence,":[48],"and":[49,51,102,148,157,227,250],"medicine":[50],"biological":[52],"research.":[53],"Although":[54],"techniques":[56,79],"for":[57,83,111,125,140,162,216,221,228],"similarity":[58,86,92,114,128,146,201,206,243],"analysis":[59],"have":[60,167],"been":[61,69],"proposed":[62,254],"past,":[65],"little":[66,168],"work":[67],"has":[68],"done":[70],"on":[71,256],"question":[73],"which":[75,113,196],"presented":[78],"are":[80,197],"suitable":[82],"task.":[88],"Knowing":[89],"right":[91],"function":[93],"important":[95],"highly":[100],"domain-":[101],"data-dependent.":[103],"In":[104,160],"this":[105],"thesis,":[106],"we":[107,183,204],"provide":[108,214],"approach":[110,133,255],"recommending":[112],"functions":[115,147,207],"edit":[117],"distance":[118],"jaccard":[120],"similarity)":[121],"should":[122],"be":[123],"used":[124],"measuring":[126],"between":[129],"two":[130],"entities.":[131],"employs":[134],"incremental":[136],"knowledge":[137,144,171],"acquisition":[138],"technique":[139],"capturing":[141,217],"domain":[142,165,218,230],"experts'":[143,219],"about":[145,172],"their":[149],"usage":[150],"contexts":[151],"class,":[154],"attribute":[155,194,225],"name":[156],"some":[158],"keywords).":[159],"addition,":[161],"situations":[163],"where":[164],"experts":[166,231],"no":[170],"datasets":[173,259],"(for":[174],"example,":[175],"when":[176,199],"they":[177],"face":[178],"\\textit{new}":[179],"\\textit{different}":[181],"ones),":[182],"analyze":[184],"features":[186,223],"misspellings":[188],"word":[190],"orders)":[191],"from":[192,224,260],"values,":[195],"considerable":[198],"selecting":[200],"functions.":[202,244],"Then,":[203],"recommend":[205],"according":[208],"to":[209,236],"identified":[211],"features.":[212],"We":[213,245],"tools":[215],"knowledge,":[220],"analyzing":[222],"data,":[226],"assisting":[229],"finding":[233],"query":[239],"using":[241],"recommended":[242],"also":[246],"demonstrate":[247],"feasibility":[249],"effectiveness":[251],"our":[253],"several":[257],"real-world":[258],"different":[261],"domains.":[262]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}