{"id":"https://openalex.org/W1529097724","doi":"https://doi.org/10.1007/11573067_20","title":"On Sample Size and Classification Accuracy: A Performance Comparison","display_name":"On Sample Size and Classification Accuracy: A Performance Comparison","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W1529097724","doi":"https://doi.org/10.1007/11573067_20","mag":"1529097724"},"language":"en","primary_location":{"id":"doi:10.1007/11573067_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11573067_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5050880128","display_name":"Margarita Sordo","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margarita Sordo","raw_affiliation_strings":["Decision Systems Group, Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Decision Systems Group, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210143601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047536976","display_name":"Qing Zeng","orcid":"https://orcid.org/0000-0002-3439-7179"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Zeng","raw_affiliation_strings":["Decision Systems Group, Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Decision Systems Group, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210143601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.2323,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.78682155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.7393808960914612},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.621691882610321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6031952500343323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5584059953689575},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5114249587059021},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5057754516601562},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4914807081222534},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.48354434967041016},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48195549845695496},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4546937346458435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4095606803894043},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.33988645672798157},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2370166778564453},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11276388168334961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7393808960914612},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.621691882610321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6031952500343323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5584059953689575},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5114249587059021},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5057754516601562},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4914807081222534},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48354434967041016},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48195549845695496},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4546937346458435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4095606803894043},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33988645672798157},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2370166778564453},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11276388168334961},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/11573067_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11573067_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1479807131","https://openalex.org/W1482934285","https://openalex.org/W1550206324","https://openalex.org/W1574901103","https://openalex.org/W1600295424","https://openalex.org/W1601162575","https://openalex.org/W2002645541","https://openalex.org/W2063198646","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W2163614729","https://openalex.org/W2170654002","https://openalex.org/W2440833291","https://openalex.org/W2911282854","https://openalex.org/W2914453346","https://openalex.org/W4237265687"],"related_works":["https://openalex.org/W4389954502","https://openalex.org/W2771255398","https://openalex.org/W2930428186","https://openalex.org/W3200027047","https://openalex.org/W4385770464","https://openalex.org/W4224262160","https://openalex.org/W3120363735","https://openalex.org/W4214820172","https://openalex.org/W2394323384","https://openalex.org/W1577730984"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}