{"id":"https://openalex.org/W4254399053","doi":"https://doi.org/10.23919/icact.2018.8323786","title":"String vector based KNN for text categorization","display_name":"String vector based KNN for text categorization","publication_year":2018,"publication_date":"2018-02-01","ids":{"openalex":"https://openalex.org/W4254399053","doi":"https://doi.org/10.23919/icact.2018.8323786"},"language":"en","primary_location":{"id":"doi:10.23919/icact.2018.8323786","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact.2018.8323786","pdf_url":null,"source":{"id":"https://openalex.org/S4363608106","display_name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","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/A5049496911","display_name":"Taeho Jo","orcid":"https://orcid.org/0000-0001-7448-9433"},"institutions":[{"id":"https://openalex.org/I94588446","display_name":"Hongik University","ror":"https://ror.org/00egdv862","country_code":"KR","type":"education","lineage":["https://openalex.org/I94588446"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Taeho Jo","raw_affiliation_strings":["School of Games Hongik University Sejong, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Games Hongik University Sejong, South Korea","institution_ids":["https://openalex.org/I94588446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5049496911"],"corresponding_institution_ids":["https://openalex.org/I94588446"],"apc_list":null,"apc_paid":null,"fwci":0.077,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51262019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"438","last_page":"443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9968000054359436,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9908000230789185,"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/string","display_name":"String (physics)","score":0.675042450428009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.626453161239624},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5879860520362854},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5810720920562744},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.5354872345924377},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5155960917472839},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5045984983444214},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4621025323867798},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.44272685050964355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4257259964942932},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.368166983127594},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36208873987197876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2684440612792969},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.09483999013900757}],"concepts":[{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.675042450428009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.626453161239624},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5879860520362854},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5810720920562744},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.5354872345924377},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5155960917472839},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5045984983444214},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4621025323867798},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.44272685050964355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4257259964942932},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.368166983127594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36208873987197876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2684440612792969},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.09483999013900757},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/icact.2018.8323786","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact.2018.8323786","pdf_url":null,"source":{"id":"https://openalex.org/S4363608106","display_name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321237","display_name":"Hongik University","ror":"https://ror.org/00egdv862"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W194138165","https://openalex.org/W1646134777","https://openalex.org/W1980483130","https://openalex.org/W1991122732","https://openalex.org/W2018423466","https://openalex.org/W2118020653","https://openalex.org/W2140266767","https://openalex.org/W2170960297","https://openalex.org/W3026106150","https://openalex.org/W6607947586","https://openalex.org/W6636811164","https://openalex.org/W6680570103","https://openalex.org/W6777334961"],"related_works":["https://openalex.org/W2986277685","https://openalex.org/W2519145296","https://openalex.org/W2590193441","https://openalex.org/W2187092961","https://openalex.org/W2187002734","https://openalex.org/W2257399947","https://openalex.org/W2051764263","https://openalex.org/W4288309913","https://openalex.org/W2998410131","https://openalex.org/W2462428821"],"abstract_inverted_index":{"This":[0],"research":[1,116],"proposes":[2],"the":[3,9,12,15,28,38,53,68,77,82,92,100,120],"string":[4,62,72,85],"vector":[5,86],"based":[6],"version":[7,30,83],"of":[8,31,65,106,114],"KNN":[10,78],"as":[11],"approach":[13],"to":[14,37,51,118],"text":[16,121],"categorization.":[17],"Traditionally,":[18],"texts":[19,58],"should":[20],"be":[21],"encoded":[22,60],"into":[23,61,81],"numerical":[24,66],"vectors":[25,73],"for":[26],"using":[27],"traditional":[29],"KNN,":[32],"and":[33,46,76,109],"encoding":[34],"so":[35],"leads":[36],"three":[39],"main":[40],"problems:":[41],"huge":[42],"dimensionality,":[43],"sparse":[44],"distribution,":[45],"poor":[47],"transparency.":[48,111],"In":[49],"order":[50],"solve":[52],"problems,":[54],"in":[55],"this":[56,95,115],"research,":[57,96],"are":[59],"vectors,":[63,67],"instead":[64],"similarity":[69],"measure":[70],"between":[71],"is":[74,79,87,117],"defined,":[75],"modified":[80],"where":[84],"given":[88],"its":[89],"input.":[90],"As":[91],"benefits":[93],"from":[94],"we":[97],"may":[98],"expect":[99],"better":[101,110],"performance,":[102],"more":[103],"compact":[104],"representation":[105],"each":[107],"text,":[108],"The":[112],"goal":[113],"improve":[119],"categorization":[122],"performance":[123],"by":[124],"solving":[125],"them.":[126]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}