{"id":"https://openalex.org/W1986471536","doi":"https://doi.org/10.1109/dsaa.2014.7058134","title":"Toward robust classification using the Open Directory Project","display_name":"Toward robust classification using the Open Directory Project","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1986471536","doi":"https://doi.org/10.1109/dsaa.2014.7058134","mag":"1986471536"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa.2014.7058134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa.2014.7058134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Data Science and Advanced Analytics (DSAA)","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/A5008817091","display_name":"JongWoo Ha","orcid":"https://orcid.org/0009-0003-6475-4119"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"JongWoo Ha","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea","Korea University, Seoul\u00a0, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University, Seoul\u00a0, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777396","display_name":"Jung\u2010Hyun Lee","orcid":"https://orcid.org/0000-0002-9662-1703"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Hyun Lee","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea","Korea University, Seoul\u00a0, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University, Seoul\u00a0, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031882012","display_name":"Won-Jun Jang","orcid":"https://orcid.org/0000-0002-5581-1578"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won-Jun Jang","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea","Korea University, Seoul\u00a0, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University, Seoul\u00a0, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048651894","display_name":"Yong-Ku Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong-Ku Lee","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea","Korea University, Seoul\u00a0, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University, Seoul\u00a0, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101595608","display_name":"SangKeun Lee","orcid":"https://orcid.org/0000-0002-6249-8217"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SangKeun Lee","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea","Korea University, Seoul\u00a0, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University, Seoul\u00a0, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008817091"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":1.44894316,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84732425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"607","last_page":"612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.987500011920929,"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/directory","display_name":"Directory","score":0.8017287254333496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8017116785049438},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6855111122131348},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.597830057144165},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5770943760871887},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5714996457099915},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47755107283592224},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4441543519496918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3522518575191498},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3217015564441681}],"concepts":[{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.8017287254333496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017116785049438},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6855111122131348},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.597830057144165},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5770943760871887},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5714996457099915},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47755107283592224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4441543519496918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3522518575191498},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3217015564441681},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa.2014.7058134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa.2014.7058134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1523949738","https://openalex.org/W1532325895","https://openalex.org/W1550206324","https://openalex.org/W1972640883","https://openalex.org/W2013477326","https://openalex.org/W2023408138","https://openalex.org/W2025047573","https://openalex.org/W2042200090","https://openalex.org/W2042774659","https://openalex.org/W2056947815","https://openalex.org/W2059792214","https://openalex.org/W2073448073","https://openalex.org/W2073830447","https://openalex.org/W2080186966","https://openalex.org/W2098876286","https://openalex.org/W2105573333","https://openalex.org/W2150766729","https://openalex.org/W2153635508","https://openalex.org/W2165612380","https://openalex.org/W2423784265","https://openalex.org/W4213009331","https://openalex.org/W6631156306","https://openalex.org/W6632865047"],"related_works":["https://openalex.org/W3115906952","https://openalex.org/W3134811395","https://openalex.org/W3155196058","https://openalex.org/W4252960523","https://openalex.org/W1529821365","https://openalex.org/W2135486207","https://openalex.org/W1499611046","https://openalex.org/W3024420453","https://openalex.org/W2388608119","https://openalex.org/W2131202893"],"abstract_inverted_index":{"The":[0],"Open":[1],"Directory":[2],"Project":[3],"(ODP)":[4],"is":[5,68,77,125],"a":[6,53],"large":[7],"scale,":[8],"high":[9],"quality":[10],"and":[11,20,70,105,118,121],"publicly":[12],"available":[13],"web":[14],"directory":[15],"utilized":[16],"in":[17],"many":[18],"studies":[19],"real-world":[21],"applications.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"explore":[27],"training":[28,66,75,87,114,134],"data":[29,67,76,88,115],"expansion":[30,89],"techniques":[31],"for":[32],"text":[33],"classification":[34,55,93],"as":[35],"one":[36],"of":[37,47],"the":[38,44,48,73,92,132],"possible":[39],"directions":[40],"to":[41,79,112,127,130],"deal":[42],"with":[43],"sparse":[45],"characteristic":[46],"ODP":[49],"dataset.":[50],"We":[51,99],"propose":[52],"dozen":[54],"methods,":[56],"which":[57,64],"can":[58],"be":[59],"differentiated":[60],"by":[61],"(1)":[62,103],"from":[63],"categories":[65,107],"expanded,":[69],"(2)":[71,122],"how":[72],"expanded":[74,133],"merged":[78],"generate":[80],"centroid":[81],"vectors.":[82],"Evaluation":[83],"results":[84],"show":[85],"that":[86,102],"significantly":[90],"improves":[91],"performance":[94],"more":[95,109],"than":[96,116],"representative":[97],"classifiers.":[98],"also":[100],"find":[101],"child":[104],"descendant":[106],"are":[108],"valuable":[110],"sources":[111],"expand":[113],"parent":[117],"ancestor":[119],"categories,":[120],"distance-based":[123],"weighting":[124],"superior":[126],"simple":[128],"averaging":[129],"merge":[131],"data.":[135]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}