{"id":"https://openalex.org/W2971463042","doi":"https://doi.org/10.1109/codit.2019.8820497","title":"String similarity algorithms for a ticket classification system","display_name":"String similarity algorithms for a ticket classification system","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2971463042","doi":"https://doi.org/10.1109/codit.2019.8820497","mag":"2971463042"},"language":"en","primary_location":{"id":"doi:10.1109/codit.2019.8820497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit.2019.8820497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5107888409","display_name":"M. Pikies","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malgorzata Pikies","raw_affiliation_strings":["Cloudflare, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloudflare, London, United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030138105","display_name":"Junade Ali","orcid":"https://orcid.org/0000-0002-0180-070X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junade Ali","raw_affiliation_strings":["Cloudflare, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloudflare, London, United Kingdom","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9973999857902527,"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/T12016","display_name":"Web Data Mining and Analysis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/longest-common-subsequence-problem","display_name":"Longest common subsequence problem","score":0.724251925945282},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6994880437850952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947358250617981},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.6516051292419434},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6454802751541138},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6039911508560181},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.6016438603401184},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5972347259521484},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5630795359611511},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4950107932090759},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.47759103775024414},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4707014560699463},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46452009677886963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4459472894668579},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.44589757919311523},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4358750283718109},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.41492247581481934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39857035875320435},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.3396819233894348},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18003049492835999},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10162988305091858}],"concepts":[{"id":"https://openalex.org/C120098539","wikidata":"https://www.wikidata.org/wiki/Q141001","display_name":"Longest common subsequence problem","level":2,"score":0.724251925945282},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6994880437850952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947358250617981},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.6516051292419434},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6454802751541138},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6039911508560181},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.6016438603401184},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5972347259521484},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5630795359611511},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4950107932090759},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.47759103775024414},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4707014560699463},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46452009677886963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4459472894668579},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.44589757919311523},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4358750283718109},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.41492247581481934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39857035875320435},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3396819233894348},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18003049492835999},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10162988305091858},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit.2019.8820497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit.2019.8820497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","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":18,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1562224794","https://openalex.org/W1828150029","https://openalex.org/W1970026646","https://openalex.org/W2016871293","https://openalex.org/W2043481183","https://openalex.org/W2109966155","https://openalex.org/W2111643688","https://openalex.org/W2156279557","https://openalex.org/W2163993443","https://openalex.org/W2165612380","https://openalex.org/W2166292125","https://openalex.org/W2238866705","https://openalex.org/W2581216160","https://openalex.org/W2812904942","https://openalex.org/W2897540080","https://openalex.org/W4213009331","https://openalex.org/W6684432063"],"related_works":["https://openalex.org/W2461708070","https://openalex.org/W2950268498","https://openalex.org/W1505906253","https://openalex.org/W2759575792","https://openalex.org/W4280559639","https://openalex.org/W4285090010","https://openalex.org/W4292436243","https://openalex.org/W2102443632","https://openalex.org/W2187092961","https://openalex.org/W2167648075"],"abstract_inverted_index":{"Fuzzy":[0],"string":[1,42],"matching":[2,9],"allows":[3],"for":[4,40,130,138],"close,":[5],"but":[6],"not":[7],"exactly,":[8],"strings":[10,122,146],"to":[11,75,135,143,159,169],"be":[12,136],"compared":[13],"and":[14,30,35,55,73,87],"extracted":[15],"from":[16],"bodies":[17],"of":[18,70,79,115,141,151,166],"text.":[19],"As":[20],"such,":[21],"they":[22],"are":[23,96,101],"useful":[24],"in":[25,90,163],"systems":[26],"which":[27],"automatically":[28,76],"extract":[29],"process":[31],"documents.":[32],"We":[33],"summarise":[34],"compare":[36],"various":[37,139],"existing":[38,175],"algorithms":[39,72],"achieving":[41],"similarity":[43,118,133],"measures:":[44],"Longest":[45],"Common":[46],"Subsequence":[47],"(LCS),":[48],"Dice":[49],"coefficient,":[50],"Cosine":[51],"Similarity,":[52],"Levenshtein":[53],"distance":[54],"Damerau":[56],"distance.":[57],"Based":[58],"on":[59,112,120],"previously":[60],"classified":[61],"customer":[62,180],"support":[63,181],"enquiries":[64],"(tickets),":[65],"we":[66],"considered":[67],"the":[68,116,152,164,174],"effectiveness":[69],"different":[71],"configurations":[74],"identify":[77],"keywords":[78],"interest":[80],"(such":[81],"as":[82],"error":[83],"phrases,":[84],"product":[85],"names":[86],"warning":[88],"messages)":[89],"instances":[91],"where":[92],"such":[93],"key":[94,155],"phrases":[95],"misspelled,":[97],"copied":[98],"incorrectly":[99],"or":[100],"otherwise":[102],"differently":[103],"formed.":[104],"An":[105],"optimal":[106,149],"algorithm":[107],"selection":[108],"is":[109],"made":[110],"based":[111],"novel":[113],"studies":[114],"aforementioned":[117],"measures":[119],"text":[121],"tokenised":[123],"into":[124],"characters.":[125],"Such":[126],"analysis":[127],"also":[128],"allowed":[129],"an":[131],"optimum":[132],"threshold":[134],"identified":[137],"categories":[140],"enquiries,":[142],"reduce":[144],"mismatched":[145],"whilst":[147],"allowing":[148],"coverage":[150],"correctly":[153],"matched":[154],"phrases.":[156],"This":[157],"led":[158],"a":[160,179],"15%":[161],"improvement":[162],"ratio":[165],"false":[167],"positives":[168],"true":[170],"positive":[171],"classifications":[172],"over":[173],"approach":[176],"used":[177],"by":[178],"system.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}