{"id":"https://openalex.org/W2182929301","doi":"https://doi.org/10.2390/biecoll-jib-2011-176","title":"Improving imbalanced scientific text classification using sampling strategies and dictionaries","display_name":"Improving imbalanced scientific text classification using sampling strategies and dictionaries","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2182929301","doi":"https://doi.org/10.2390/biecoll-jib-2011-176","mag":"2182929301","pmid":"https://pubmed.ncbi.nlm.nih.gov/21926439"},"language":"en","primary_location":{"id":"pmid:21926439","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21926439","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of integrative bioinformatics","raw_type":null},"type":"article","indexed_in":["datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2390/biecoll-jib-2011-176","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064440046","display_name":"L. Borrajo","orcid":"https://orcid.org/0000-0002-6089-6166"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Borrajo, Lourdes","raw_affiliation_strings":["Univ. of Vigo, Computer Science Dept., Campus As Lagoas s/n, 32004 Ourense, Spain"],"affiliations":[{"raw_affiliation_string":"Univ. of Vigo, Computer Science Dept., Campus As Lagoas s/n, 32004 Ourense, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010854524","display_name":"R. Romero","orcid":"https://orcid.org/0000-0002-7413-2394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romero, Ruben","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034116654","display_name":"Eva Iglesias","orcid":"https://orcid.org/0000-0002-7172-6947"},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Lorenzo Iglesias, Eva","raw_affiliation_strings":["University of Vigo;"],"affiliations":[{"raw_affiliation_string":"University of Vigo;","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047872631","display_name":"C. M. Redondo Marey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Redondo Marey, Carmen Maria","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064440046"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1929,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89696811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"3","first_page":"176","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9957000017166138,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9957000017166138,"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":0.9944999814033508,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7625675797462463},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.7354316115379333},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6854475736618042},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6551601886749268},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6273782253265381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6011571288108826},{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.5281034708023071},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4813424050807953},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46362733840942383},{"id":"https://openalex.org/keywords/scientific-literature","display_name":"Scientific literature","score":0.41143161058425903},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3558667302131653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3343625068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625675797462463},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.7354316115379333},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6854475736618042},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6551601886749268},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6273782253265381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011571288108826},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.5281034708023071},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4813424050807953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46362733840942383},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.41143161058425903},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3558667302131653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3343625068664551},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"pmid:21926439","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21926439","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of integrative bioinformatics","raw_type":null},{"id":"pmh:oai:biecoll.ub.uni-bielefeld.de:5192","is_oa":false,"landing_page_url":"http://biecoll.ub.uni-bielefeld.de/volltexte/2011/5192/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://journal.imbio.de/article.php?aid=176","raw_type":"Journal Article"},{"id":"doi:10.2390/biecoll-jib-2011-176","is_oa":true,"landing_page_url":"https://doi.org/10.2390/biecoll-jib-2011-176","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.2390/biecoll-jib-2011-176","is_oa":true,"landing_page_url":"https://doi.org/10.2390/biecoll-jib-2011-176","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W124454490","https://openalex.org/W161282504","https://openalex.org/W297499026","https://openalex.org/W1481946661","https://openalex.org/W1503487158","https://openalex.org/W1576226931","https://openalex.org/W1590437321","https://openalex.org/W1591478822","https://openalex.org/W1607983314","https://openalex.org/W1965895350","https://openalex.org/W1979495886","https://openalex.org/W1986515506","https://openalex.org/W1997841190","https://openalex.org/W1999318832","https://openalex.org/W2002857471","https://openalex.org/W2005422315","https://openalex.org/W2006210519","https://openalex.org/W2053724458","https://openalex.org/W2098162425","https://openalex.org/W2102381086","https://openalex.org/W2111255192","https://openalex.org/W2116796547","https://openalex.org/W2118020653","https://openalex.org/W2119821739","https://openalex.org/W2126276057","https://openalex.org/W2138505392","https://openalex.org/W2147169507","https://openalex.org/W2149684865","https://openalex.org/W2151698208","https://openalex.org/W2152785430","https://openalex.org/W2154139219","https://openalex.org/W2155042162","https://openalex.org/W2161349060","https://openalex.org/W2165888424","https://openalex.org/W2169918010","https://openalex.org/W2170714718","https://openalex.org/W2585036687","https://openalex.org/W2917056928","https://openalex.org/W3155649056"],"related_works":["https://openalex.org/W4205958290","https://openalex.org/W2187500075","https://openalex.org/W2160451891","https://openalex.org/W1985680156","https://openalex.org/W4210936077","https://openalex.org/W2539163683","https://openalex.org/W4282031078","https://openalex.org/W2149078746","https://openalex.org/W3168994312","https://openalex.org/W3105251098"],"abstract_inverted_index":{"Many":[0],"real":[1],"applications":[2],"have":[3],"the":[4,12,25,30,37,55,83,95,100,119,125,141,145,160],"imbalanced":[5],"class":[6,58],"distribution":[7],"problem,":[8],"where":[9],"one":[10],"of":[11,21,29,41,57,70,89,97,102,118],"classes":[13],"is":[14,92],"represented":[15],"by":[16,156],"a":[17],"very":[18],"small":[19],"number":[20],"cases":[22],"compared":[23,152],"to":[24,36,80,93],"other":[26,157],"classes.":[27],"One":[28],"systems":[31],"affected":[32],"are":[33,51,78,106],"those":[34,154],"related":[35],"recovery":[38],"and":[39,49,74,114,128,137,140],"classification":[40,101],"scientific":[42,85],"documentation.":[43],"Sampling":[44],"strategies":[45],"such":[46],"as":[47],"Oversampling":[48],"Subsampling":[50,146],"popular":[52],"in":[53,99],"tackling":[54],"problem":[56],"imbalance.":[59],"In":[60],"this":[61,90],"work,":[62],"we":[63],"study":[64,94],"their":[65],"effects":[66],"on":[67,82],"three":[68,109],"types":[69],"classifiers":[71,127],"(Knn,":[72],"SVM":[73,142],"Naive-Bayes)":[75],"when":[76],"they":[77],"applied":[79],"search":[81],"PubMed":[84],"database.":[86],"Another":[87],"purpose":[88],"paper":[91],"use":[96],"dictionaries":[98,111,139],"biomedical":[103],"texts.":[104],"Experiments":[105],"conducted":[107],"with":[108,135,153],"different":[110],"(BioCreative,":[112],"NLPBA,":[113],"an":[115],"ad-hoc":[116],"subset":[117],"UniProt":[120],"database":[121],"named":[122],"Protein)":[123],"using":[124,144,159],"mentioned":[126],"sampling":[129],"strategies.":[130],"Best":[131],"results":[132,150],"were":[133,151],"obtained":[134,155],"NLPBA":[136],"Protein":[138],"classifier":[143],"balancing":[147],"technique.":[148],"These":[149],"authors":[158],"TREC":[161],"Genomics":[162],"2005":[163],"public":[164],"corpus.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}