{"id":"https://openalex.org/W2152283452","doi":"https://doi.org/10.1109/dasfaa.2003.1192375","title":"Mining emerging substrings","display_name":"Mining emerging substrings","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2152283452","doi":"https://doi.org/10.1109/dasfaa.2003.1192375","mag":"2152283452"},"language":"en","primary_location":{"id":"doi:10.1109/dasfaa.2003.1192375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dasfaa.2003.1192375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eighth International Conference on Database Systems for Advanced Applications, 2003. (DASFAA 2003). Proceedings.","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/A5064619021","display_name":"Stephen Chan","orcid":"https://orcid.org/0000-0003-0985-1074"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"S. Chan","raw_affiliation_strings":["Department of Computer Science and Information Systems, University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Systems, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063695659","display_name":"Ben Kao","orcid":"https://orcid.org/0000-0002-0501-9435"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"B. Kao","raw_affiliation_strings":["Department of Computer Science and Information Systems, University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Systems, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111442975","display_name":"Chi-Lap Yip","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"C.L. Yip","raw_affiliation_strings":["Department of Computer Science and Information Systems, University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Systems, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102907523","display_name":"M. Tang","orcid":"https://orcid.org/0009-0005-9814-0718"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"M. Tang","raw_affiliation_strings":["Department of Computer Science and Information Systems, University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Systems, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064619021"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":3.9947,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.94624575,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987999796867371,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9984999895095825,"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/T11106","display_name":"Data Management and Algorithms","score":0.9319000244140625,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/substring","display_name":"Substring","score":0.9696754217147827},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7622588872909546},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7479956150054932},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.6812030076980591},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6718594431877136},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5522361993789673},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5272770524024963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5246046781539917},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.4542447030544281},{"id":"https://openalex.org/keywords/class-hierarchy","display_name":"Class hierarchy","score":0.42293238639831543},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.41383036971092224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3466367721557617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33415687084198},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.29237544536590576}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9696754217147827},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7622588872909546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479956150054932},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.6812030076980591},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6718594431877136},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5522361993789673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5272770524024963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246046781539917},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.4542447030544281},{"id":"https://openalex.org/C2781289151","wikidata":"https://www.wikidata.org/wiki/Q2903989","display_name":"Class hierarchy","level":3,"score":0.42293238639831543},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.41383036971092224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3466367721557617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33415687084198},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29237544536590576},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dasfaa.2003.1192375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dasfaa.2003.1192375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eighth International Conference on Database Systems for Advanced Applications, 2003. (DASFAA 2003). Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.14.8864","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.8864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csis.hku.hk/research/techreps/document/TR-2002-11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1481102362","https://openalex.org/W1485516007","https://openalex.org/W1504694836","https://openalex.org/W1506285740","https://openalex.org/W1527513100","https://openalex.org/W1533946607","https://openalex.org/W1539666472","https://openalex.org/W1569729202","https://openalex.org/W1571053466","https://openalex.org/W1935694007","https://openalex.org/W1955600018","https://openalex.org/W1983072039","https://openalex.org/W1984599184","https://openalex.org/W2038812321","https://openalex.org/W2072069204","https://openalex.org/W2100176599","https://openalex.org/W2111581885","https://openalex.org/W2121252285","https://openalex.org/W2125055259","https://openalex.org/W2126146704","https://openalex.org/W2141115288","https://openalex.org/W2152283452","https://openalex.org/W2154642793","https://openalex.org/W2160605849","https://openalex.org/W4241634004","https://openalex.org/W4247964656","https://openalex.org/W6628841842","https://openalex.org/W6630198464","https://openalex.org/W6632805256","https://openalex.org/W6633831026","https://openalex.org/W6640950511","https://openalex.org/W6675462168","https://openalex.org/W6678449394","https://openalex.org/W6682592150","https://openalex.org/W6682837551","https://openalex.org/W6683599321"],"related_works":["https://openalex.org/W2070949798","https://openalex.org/W96331545","https://openalex.org/W2102450363","https://openalex.org/W2162655434","https://openalex.org/W3022344494","https://openalex.org/W1548907175","https://openalex.org/W1608420182","https://openalex.org/W2583658747","https://openalex.org/W1882920571","https://openalex.org/W2067956663"],"abstract_inverted_index":{"We":[0,61],"introduce":[1],"a":[2,12,20,24,63,99],"new":[3],"type":[4],"of":[5,19,58,74,84,98,118],"KDD":[6],"patterns":[7],"called":[8],"emerging":[9,16],"substrings.":[10],"In":[11],"sequence":[13,42,59],"database,":[14,107],"an":[15],"substring":[17,25],"(ES)":[18],"data":[21,50],"class":[22,32,96],"is":[23,97,109],"which":[26,108],"occurs":[27],"more":[28,78],"frequently":[29],"in":[30,35,81,113],"that":[31,92],"rather":[33],"than":[34],"other":[36],"classes.":[37],"ESs":[38],"are":[39],"important":[40],"to":[41,104],"classification":[43],"as":[44],"they":[45],"capture":[46],"significant":[47],"contrasts":[48],"between":[49],"classes":[51],"and":[52,70],"provide":[53],"insights":[54],"for":[55,67],"the":[56,72,94,105,110,119],"construction":[57],"classifiers.":[60],"propose":[62],"suffix":[64],"tree-based":[65],"framework":[66],"mining":[68,87],"ESs,":[69],"study":[71],"effectiveness":[73],"applying":[75],"one":[76],"or":[77],"pruning":[79,120],"techniques":[80,121],"different":[82],"stages":[83],"our":[85],"ES":[86,115],"algorithm.":[88],"Experimental":[89],"results":[90],"show":[91],"if":[93],"target":[95],"small":[100],"population":[101],"with":[102],"respect":[103],"whole":[106],"normal":[111],"scenario":[112],"single-class":[114],"mining,":[116],"most":[117],"would":[122],"achieve":[123],"considerable":[124],"performance":[125],"gain.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
