{"id":"https://openalex.org/W2028431844","doi":"https://doi.org/10.1145/2806416.2806453","title":"Approximate String Matching by End-Users using Active Learning","display_name":"Approximate String Matching by End-Users using Active Learning","publication_year":2015,"publication_date":"2015-10-17","ids":{"openalex":"https://openalex.org/W2028431844","doi":"https://doi.org/10.1145/2806416.2806453","mag":"2028431844"},"language":"en","primary_location":{"id":"doi:10.1145/2806416.2806453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","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/A5088938582","display_name":"Lutz B\u00fcch","orcid":"https://orcid.org/0000-0003-1398-0565"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lutz B\u00fcch","raw_affiliation_strings":["Heidelberg University, Germany, Heidelberg, Germany","Heidelberg University, Germany, Heidelberg, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Heidelberg University, Germany, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University, Germany, Heidelberg, Germany#TAB#","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054003032","display_name":"Artur Andrzejak","orcid":"https://orcid.org/0000-0003-0150-8220"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Artur Andrzejak","raw_affiliation_strings":["Heidelberg University, Germany, Heidelberg, Germany","Heidelberg University, Germany, Heidelberg, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Heidelberg University, Germany, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University, Germany, Heidelberg, Germany#TAB#","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088938582"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":0.4006,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69211985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9944000244140625,"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/string-metric","display_name":"String metric","score":0.8215833902359009},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7871204018592834},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7682335376739502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7408470511436462},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6420180797576904},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6103439331054688},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.548180103302002},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5284238457679749},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5019910335540771},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.4981973171234131},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4871058464050293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47737404704093933},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4335900545120239},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.425650954246521},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.4161338210105896},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.3940148949623108},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1443256437778473},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07557210326194763}],"concepts":[{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.8215833902359009},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7871204018592834},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7682335376739502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408470511436462},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6420180797576904},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6103439331054688},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.548180103302002},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5284238457679749},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5019910335540771},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.4981973171234131},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4871058464050293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47737404704093933},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4335900545120239},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.425650954246521},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.4161338210105896},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3940148949623108},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1443256437778473},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07557210326194763},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":1,"locations":[{"id":"doi:10.1145/2806416.2806453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1646278814","https://openalex.org/W1995099886","https://openalex.org/W2008896880","https://openalex.org/W2036216970","https://openalex.org/W2039001182","https://openalex.org/W2042913039","https://openalex.org/W2047583926","https://openalex.org/W2052581258","https://openalex.org/W2065259291","https://openalex.org/W2067497031","https://openalex.org/W2094834818","https://openalex.org/W2097184821","https://openalex.org/W2099485165","https://openalex.org/W2104511295","https://openalex.org/W2150698190","https://openalex.org/W2170902582","https://openalex.org/W2288244345","https://openalex.org/W2295240344","https://openalex.org/W2914331073","https://openalex.org/W6696516842"],"related_works":["https://openalex.org/W2187092961","https://openalex.org/W2257399947","https://openalex.org/W2405436873","https://openalex.org/W52396946","https://openalex.org/W2371263218","https://openalex.org/W2399644331","https://openalex.org/W2141423589","https://openalex.org/W2386746909","https://openalex.org/W2037600093","https://openalex.org/W2245915510"],"abstract_inverted_index":{"Identifying":[0],"approximately":[1],"identical":[2],"strings":[3],"is":[4,47],"key":[5],"for":[6,36],"many":[7],"data":[8,11],"cleaning":[9],"and":[10,17,34,45],"integration":[12],"processes,":[13],"including":[14],"similarity":[15,32,43],"join":[16],"record":[18],"matching.":[19],"The":[20],"accuracy":[21],"of":[22,30,42,55],"such":[23],"tasks":[24],"crucially":[25],"depends":[26],"on":[27,52],"appropriate":[28],"choices":[29],"string":[31],"measures":[33,44],"thresholds":[35,46],"the":[37,53],"particular":[38],"dataset.":[39],"Manual":[40],"selection":[41],"infeasible.":[48],"Other":[49],"approaches":[50],"rely":[51],"existence":[54],"adequate":[56],"historic":[57],"ground-truth":[58],"or":[59],"massive":[60],"manual":[61],"effort.":[62]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}