{"id":"https://openalex.org/W7125898971","doi":"https://doi.org/10.1109/smc58881.2025.11343499","title":"Text-based entity matching for entity resolution and data fusion applied to person descriptions","display_name":"Text-based entity matching for entity resolution and data fusion applied to person descriptions","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125898971","doi":"https://doi.org/10.1109/smc58881.2025.11343499"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5115027094","display_name":"Jan Nausner","orcid":null},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jan Nausner","raw_affiliation_strings":["Austrian Institute of Technology,Cooperative Digital Technologies, Center for Digital Safety and Security,Vienna,Austria,1210"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology,Cooperative Digital Technologies, Center for Digital Safety and Security,Vienna,Austria,1210","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124129060","display_name":"Jakob Hurst","orcid":null},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jakob Hurst","raw_affiliation_strings":["Austrian Institute of Technology,Cooperative Digital Technologies, Center for Digital Safety and Security,Vienna,Austria,1210"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology,Cooperative Digital Technologies, Center for Digital Safety and Security,Vienna,Austria,1210","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101668290","display_name":"Michael H\u00fcbner","orcid":"https://orcid.org/0000-0002-1640-5614"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Hubner","raw_affiliation_strings":["Austrian Institute of Technology,Cooperative Digital Technologies, Center for Digital Safety and Security,Vienna,Austria,1210"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology,Cooperative Digital Technologies, Center for Digital Safety and Security,Vienna,Austria,1210","institution_ids":["https://openalex.org/I132118926"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62466803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7080","last_page":"7085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.2851000130176544,"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"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.2851000130176544,"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"}},{"id":"https://openalex.org/T12740","display_name":"Gait Recognition and Analysis","score":0.25769999623298645,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.12080000340938568,"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/matching","display_name":"Matching (statistics)","score":0.7506999969482422},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5430999994277954},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5325999855995178},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5245000123977661},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/feature-matching","display_name":"Feature matching","score":0.39570000767707825},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.36649999022483826},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.33340001106262207},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.3325999975204468}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7506999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6987000107765198},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5430999994277954},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5325999855995178},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3977000117301941},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.39570000767707825},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.3208000063896179},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C61455927","wikidata":"https://www.wikidata.org/wiki/Q1030529","display_name":"Blossom algorithm","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1981590391","https://openalex.org/W2005898564","https://openalex.org/W2101234009","https://openalex.org/W2546672044","https://openalex.org/W2592051407","https://openalex.org/W2604463754","https://openalex.org/W2798649495","https://openalex.org/W2963449390","https://openalex.org/W2988823324","https://openalex.org/W3014705052","https://openalex.org/W3048871918","https://openalex.org/W3080592272","https://openalex.org/W3092962901","https://openalex.org/W3119752913","https://openalex.org/W3138971549","https://openalex.org/W3206868111","https://openalex.org/W4221163653","https://openalex.org/W4321448364","https://openalex.org/W4383051975","https://openalex.org/W4387969466","https://openalex.org/W4403021789","https://openalex.org/W4413457439"],"related_works":[],"abstract_inverted_index":{"Text-based":[0,96],"entity":[1,16,90],"matching":[2,17,36,91,104,164],"facilitates":[3],"interoperability":[4],"between":[5],"heterogeneous":[6],"systems":[7],"by":[8,43],"aligning":[9],"textual":[10,162],"person":[11,35,46,103,163],"descriptions.":[12],"We":[13,38],"propose":[14],"an":[15,135],"methodology":[18],"that":[19],"integrates":[20],"rule-based":[21],"feature":[22,41],"extraction,":[23],"similarity":[24,55],"measures,":[25],"and":[26,57,77,100,114,151],"supervised":[27,69],"machine":[28],"learning":[29],"classifiers,":[30],"rigorously":[31],"evaluated":[32,67],"on":[33],"a":[34,40,51,87,152,167],"problem.":[37],"constructed":[39],"space":[42],"extracting":[44],"domain-specific":[45,89],"attributes":[47],"from":[48],"text":[49],"via":[50],"combination":[52],"of":[53,59,106,111,124,137,155],"string":[54],"scores":[56],"similarities":[58],"inverse":[60],"document":[61],"frequency":[62],"(TF-IDF)":[63],"embeddings.":[64],"Next,":[65],"we":[66,85,119],"multiple":[68],"classification":[70,112,122],"models":[71,108],"including":[72],"Multi-Layer":[73],"Perceptron,":[74],"Random":[75],"Forest,":[76],"XGBoost,":[78],"to":[79,133,143,148],"determine":[80],"their":[81],"effectiveness.":[82],"For":[83],"evaluation,":[84],"created":[86],"new":[88],"dataset":[92],"named":[93],"Real":[94],"Scenario":[95],"Person":[97],"Matching":[98],"(RSTPM),":[99],"assessed":[101],"the":[102,121,125,149],"performance":[105],"all":[107],"in":[109,145,161,170],"terms":[110],"metrics":[113],"computational":[115,171],"cost.":[116],"In":[117],"addition,":[118],"studied":[120],"impact":[123],"various":[126],"features.":[127],"The":[128],"proposed":[129],"approach":[130],"was":[131],"shown":[132],"achieve":[134],"increase":[136,169],"27.47":[138],"percentage":[139],"points":[140],"(from":[141],"55.41%":[142],"82.88%)":[144],"F1-Score":[146],"compared":[147],"baseline":[150],"total":[153],"Accuracy":[154],"92.14%,":[156],"thus":[157],"demonstrating":[158],"significant":[159],"improvements":[160],"whilst":[165],"exhibiting":[166],"moderate":[168],"demand.":[172]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-29T00:00:00"}