{"id":"https://openalex.org/W2889910479","doi":"https://doi.org/10.1109/inista.2018.8466294","title":"Effective Unsupervised Matching of Product Titles with k-Combinations and Permutations","display_name":"Effective Unsupervised Matching of Product Titles with k-Combinations and Permutations","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2889910479","doi":"https://doi.org/10.1109/inista.2018.8466294","mag":"2889910479"},"language":"en","primary_location":{"id":"doi:10.1109/inista.2018.8466294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/inista.2018.8466294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Innovations in Intelligent Systems and Applications (INISTA)","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/A5011200753","display_name":"Leonidas Akritidis","orcid":"https://orcid.org/0000-0001-6602-0723"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Leonidas Akritidis","raw_affiliation_strings":["Data Structuring & Engineering Lab, University of Thessaly, Volos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Structuring & Engineering Lab, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011619520","display_name":"Panayiotis Bozanis","orcid":"https://orcid.org/0000-0001-9435-1829"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panayiotis Bozanis","raw_affiliation_strings":["Data Structuring & Engineering Lab, University of Thessaly, Volos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Structuring & Engineering Lab, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7613,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.86385899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9975000023841858,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9898999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7663953900337219},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7353187799453735},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.6782834529876709},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6364365220069885},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6350677013397217},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6205681562423706},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5587090849876404},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5476197600364685},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4998514652252197},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.48711109161376953},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3658698797225952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2579798996448517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14661002159118652},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11888453364372253},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11710050702095032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663953900337219},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7353187799453735},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.6782834529876709},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6364365220069885},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6350677013397217},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6205681562423706},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5587090849876404},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5476197600364685},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4998514652252197},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.48711109161376953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3658698797225952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2579798996448517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14661002159118652},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11888453364372253},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11710050702095032},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.1109/inista.2018.8466294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/inista.2018.8466294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Innovations in Intelligent Systems and Applications (INISTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/70352","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/70352","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2018 IEEE (SMC) International Conference on Innovations in Intelligent Systems and Applications, INISTA 2018","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W41404523","https://openalex.org/W86887328","https://openalex.org/W1532325895","https://openalex.org/W1536860849","https://openalex.org/W1541691357","https://openalex.org/W1582775886","https://openalex.org/W1748393397","https://openalex.org/W1981590391","https://openalex.org/W1994714765","https://openalex.org/W1997927541","https://openalex.org/W2024105308","https://openalex.org/W2034190452","https://openalex.org/W2040925009","https://openalex.org/W2044163187","https://openalex.org/W2045929671","https://openalex.org/W2065259291","https://openalex.org/W2097184821","https://openalex.org/W2104511295","https://openalex.org/W2105423800","https://openalex.org/W2108991785","https://openalex.org/W2110166424","https://openalex.org/W2123402141","https://openalex.org/W2125587588","https://openalex.org/W2162362997","https://openalex.org/W2164456230","https://openalex.org/W2171313960","https://openalex.org/W2295145075","https://openalex.org/W3146259567","https://openalex.org/W4213009331","https://openalex.org/W6601696544","https://openalex.org/W6603544577","https://openalex.org/W6632287896","https://openalex.org/W6656431919","https://openalex.org/W6660619652","https://openalex.org/W6676652611"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"The":[0,15,38,240,256],"problem":[1],"of":[2,7,24,44,58,155,163,185,188,207,210,249,259],"matching":[3,283],"product":[4,72,87],"titles":[5,73,139,187,212],"is":[6,121,131,179,244],"particular":[8],"interest":[9],"for":[10,85],"both":[11],"users":[12],"and":[13,27,31,48,111,126,161,178,213,222,285],"marketers.":[14],"former,":[16],"frequently":[17],"search":[18,77,159],"the":[19,22,71,95,100,107,114,117,142,156,182,186,189,200,205,208,211,226,250,260],"Web":[20,76],"with":[21],"aim":[23],"comparing":[25],"prices":[26,47],"characteristics,":[28],"or":[29,137],"obtaining":[30],"aggregating":[32],"information":[33,232],"provided":[34],"by":[35,74],"other":[36],"users.":[37],"latter,":[39],"often":[40],"require":[41],"wide":[42],"knowledge":[43],"competitive":[45],"policies,":[46],"features":[49],"to":[50,69,133,141,233,237,270,280],"organize":[51],"a":[52,56,89,128,170,235,263],"promotional":[53],"campaign":[54],"about":[55],"group":[57],"products.":[59,190],"To":[60],"address":[61],"this":[62,166,231],"interesting":[63],"problem,":[64],"recent":[65],"studies":[66],"have":[67,97,148],"attempted":[68],"enrich":[70],"exploiting":[75],"engines.":[78],"More":[79],"specifically,":[80],"these":[81,146,176],"methods":[82,147],"suggest":[83],"that":[84,268],"each":[86,119,238,254],"title":[88],"query":[90],"should":[91],"be":[92],"submitted.":[93],"After":[94],"results":[96,108],"been":[98],"collected,":[99],"most":[101],"important":[102],"words":[103,209],"which":[104,173,252],"appear":[105],"in":[106,113,196,262],"are":[109],"identified":[110],"appended":[112],"titles.":[115],"In":[116,165,191,199,225],"sequel,":[118],"word":[120,220],"assigned":[122],"an":[123],"importance":[124],"score":[125,236],"finally,":[127],"similarity":[129,274],"measure":[130],"applied":[132],"identify":[134],"if":[135],"two":[136,197],"more":[138],"refer":[140],"same":[143],"product.":[144,255],"Nonetheless,":[145],"multiple":[149],"problems":[150],"including":[151],"scalability,":[152],"slow":[153],"retrieval":[154],"required":[157],"additional":[158],"results,":[160],"lack":[162],"flexibility.":[164],"paper,":[167],"we":[168,203,214,229],"present":[169],"different":[171],"approach":[172,277],"addresses":[174],"all":[175],"issues":[177],"based":[180],"on":[181],"morphological":[183],"analysis":[184],"particular,":[192],"our":[193,276],"method":[194],"operates":[195],"phases.":[198],"first":[201],"phase,":[202,228],"compute":[204],"combinations":[206],"record":[215],"several":[216],"statistics":[217],"such":[218],"as":[219,247],"proximity":[221],"frequency":[223],"values.":[224],"second":[227],"use":[230],"assign":[234],"combination.":[239],"highest":[241],"scoring":[242],"combination":[243],"then":[245],"declared":[246],"label":[248],"cluster":[251],"contains":[253],"experimental":[257],"evaluation":[258],"algorithm,":[261],"real":[264],"world":[265],"dataset,":[266],"demonstrated":[267],"compared":[269],"three":[271],"popular":[272],"string":[273],"metrics,":[275],"achieves":[278],"up":[279],"36%":[281],"better":[282],"performance":[284],"at":[286],"least":[287],"13":[288],"times":[289],"faster":[290],"execution.":[291]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}