{"id":"https://openalex.org/W2168939622","doi":null,"title":"Feature Selection for Text Classification Based on Gini Coefficient of Inequality","display_name":"Feature Selection for Text Classification Based on Gini Coefficient of Inequality","publication_year":2010,"publication_date":"2010-05-26","ids":{"openalex":"https://openalex.org/W2168939622","mag":"2168939622"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.169.271","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.169.271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.csail.mit.edu/proceedings/papers/v10/sanasam10a/sanasam10a.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5101512376","display_name":"Sanasam Ranbir Singh","orcid":"https://orcid.org/0000-0003-0484-2144","observed_orcids":["https://orcid.org/0000-0003-0484-2144"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanasam Ranbir Singh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0484-2144","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550","observed_orcids":["https://orcid.org/0000-0003-3611-6550"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hema A. Murthy","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3611-6550","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025015499","display_name":"Timothy A. Gonsalves","orcid":"https://orcid.org/0000-0003-1837-4564","observed_orcids":["https://orcid.org/0000-0003-1837-4564"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy A. Gonsalves","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1837-4564","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4364,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.95806236,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/feature-selection","display_name":"feature selection","score":0.9739999771118164},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.9319999814033508},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.7960000038146973},{"id":"https://openalex.org/keywords/information-gain","display_name":"information gain","score":1.0},{"id":"https://openalex.org/keywords/chi-square-test","display_name":"chi-square test","score":0.800000011920929}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7530047297477722},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6695939898490906},{"id":"https://openalex.org/C2779206190","wikidata":"https://www.wikidata.org/wiki/Q162455","display_name":"Gini coefficient","level":4,"score":0.664535403251648},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6059319972991943},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5791937708854675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5719571113586426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559793710708618},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5188235640525818},{"id":"https://openalex.org/C45555294","wikidata":"https://www.wikidata.org/wiki/Q28113351","display_name":"Inequality","level":2,"score":0.4804227352142334},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47496768832206726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45960453152656555},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4201311469078064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3935684561729431},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35259246826171875},{"id":"https://openalex.org/C513380476","wikidata":"https://www.wikidata.org/wiki/Q5055020","display_name":"Economic inequality","level":3,"score":0.17995068430900574},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.169.271","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.169.271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.csail.mit.edu/proceedings/papers/v10/sanasam10a/sanasam10a.pdf","raw_type":"text"},{"id":"mag:2168939622","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v10/sanasam10a/sanasam10a.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1514800236","https://openalex.org/W1632356912","https://openalex.org/W2087163299","https://openalex.org/W2098162425","https://openalex.org/W2114535528","https://openalex.org/W2134606943","https://openalex.org/W2135480051","https://openalex.org/W2165612380","https://openalex.org/W2167036382","https://openalex.org/W2435251607","https://openalex.org/W2798141208"],"related_works":["https://openalex.org/W2092285120","https://openalex.org/W1626442488","https://openalex.org/W2019864860","https://openalex.org/W1999635750","https://openalex.org/W2025484710","https://openalex.org/W2382692965","https://openalex.org/W2734719344","https://openalex.org/W2536756668","https://openalex.org/W2371357422","https://openalex.org/W2383199798"],"abstract_inverted_index":{"A":[0],"number":[1],"of":[2,47,53,55,64,80,83,104],"feature":[3,39,66,116],"selection":[4,40],"mechanisms":[5],"have":[6],"been":[7],"explored":[8],"in":[9],"text":[10,75],"categorization,":[11,115],"among":[12,67],"which":[13],"mutual":[14,93],"information,":[15,94],"information":[16,95],"gain":[17,96],"and":[18,97,109],"chi-square":[19,98],"are":[20],"considered":[21],"most":[22],"effective.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,85],"study":[28],"another":[29],"method":[30],"known":[31],"as":[32],"within":[33,120],"class":[34,121],"popularity":[35,122],"to":[36],"deal":[37],"with":[38,73,100],"based":[41],"on":[42],"the":[43,61,88,92],"concept":[44],"Gini":[45],"coefficient":[46],"inequality":[48,54],"(a":[49],"commonly":[50],"used":[51],"measure":[52,59,90],"income).":[56],"The":[57],"proposed":[58,89],"explores":[60],"relative":[62],"distribution":[63],"a":[65],"different":[68,81],"classes.":[69],"From":[70],"extensive":[71],"experiments":[72],"four":[74],"classifiers":[76],"over":[77],"three":[78],"datasets":[79],"levels":[82],"heterogeneity,":[84],"observe":[86],"that":[87],"outperforms":[91],"static":[99],"an":[101],"average":[102],"improvement":[103],"approximately":[105],"28.5%,":[106],"19":[107],"%":[108,111],"9.2":[110],"respectively.":[112],"Keywords:":[113],"Text":[114],"selection,":[117],"gini":[118],"coefficient,":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}