{"id":"https://openalex.org/W2518330421","doi":"https://doi.org/10.1145/2960811.2967164","title":"Selecting Features with Class Based and Importance Weighted Document Frequency in Text Classification","display_name":"Selecting Features with Class Based and Importance Weighted Document Frequency in Text Classification","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2518330421","doi":"https://doi.org/10.1145/2960811.2967164","mag":"2518330421"},"language":"en","primary_location":{"id":"doi:10.1145/2960811.2967164","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2967164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","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/A5103324036","display_name":"Baoli Li","orcid":"https://orcid.org/0009-0009-4797-1318"},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baoli Li","raw_affiliation_strings":["Henan University of Technology, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"Henan University of Technology, Zhengzhou, China","institution_ids":["https://openalex.org/I36152291"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103324036"],"corresponding_institution_ids":["https://openalex.org/I36152291"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.055318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"139","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.998199999332428,"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":0.998199999332428,"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/T10057","display_name":"Face and Expression Recognition","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9595000147819519,"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/metric","display_name":"Metric (unit)","score":0.7444522976875305},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7381595373153687},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6341208219528198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.609119176864624},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5693186521530151},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5624865293502808},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5422793626785278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5417535901069641},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5070977210998535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45576012134552},{"id":"https://openalex.org/keywords/frequency-distribution","display_name":"Frequency distribution","score":0.4498552083969116},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39477458596229553},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3205094635486603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26398855447769165},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14983239769935608}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7444522976875305},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7381595373153687},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6341208219528198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609119176864624},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5693186521530151},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5624865293502808},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5422793626785278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5417535901069641},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5070977210998535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45576012134552},{"id":"https://openalex.org/C51921466","wikidata":"https://www.wikidata.org/wiki/Q1627586","display_name":"Frequency distribution","level":2,"score":0.4498552083969116},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39477458596229553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3205094635486603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26398855447769165},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14983239769935608},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2960811.2967164","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2967164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G6541650414","display_name":null,"funder_award_id":"2012BS027","funder_id":"https://openalex.org/F4320321955","funder_display_name":"Henan University of Technology"}],"funders":[{"id":"https://openalex.org/F4320321955","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W99763903","https://openalex.org/W1493526108","https://openalex.org/W1550206324","https://openalex.org/W1574901103","https://openalex.org/W1964042173","https://openalex.org/W2103333826","https://openalex.org/W2118585731","https://openalex.org/W2153635508","https://openalex.org/W2167101736","https://openalex.org/W2340455672","https://openalex.org/W2345944844","https://openalex.org/W2435251607","https://openalex.org/W2911681169","https://openalex.org/W2914859268","https://openalex.org/W2998216295","https://openalex.org/W3001645704","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2729514902","https://openalex.org/W2024160000","https://openalex.org/W2773500201","https://openalex.org/W2061273563","https://openalex.org/W2285052147","https://openalex.org/W4287995534","https://openalex.org/W2743258233","https://openalex.org/W2998168123","https://openalex.org/W1972656095","https://openalex.org/W2970216048"],"abstract_inverted_index":{"Document":[0],"Frequency":[1],"(DF),":[2],"which":[3,94],"counts":[4],"how":[5],"many":[6],"documents":[7],"a":[8,82,100,127],"feature":[9,24],"appears":[10],"in,":[11],"is":[12,57],"reported":[13],"by":[14],"Yang":[15],"and":[16,44,60,130],"Pedersen":[17],"[1]":[18],"to":[19,37,89],"be":[20,90],"quite":[21,46],"effective":[22],"for":[23,50],"selection":[25],"in":[26,77],"text":[27,140],"classification.":[28,51],"Features":[29],"with":[30],"the":[31,53,69,79,91,96,104,115,120,145,148],"same":[32],"DF":[33,55,106],"value":[34],"are":[35,87],"likely":[36],"have":[38],"different":[39,47,72,75],"appearance":[40],"distribution":[41,65],"over":[42,66],"categories,":[43],"demonstrate":[45],"discriminative":[48],"powers":[49],"However,":[52,103],"original":[54,121],"metric":[56,107],"class":[58,128],"independent":[59],"does":[61],"not":[62],"consider":[63],"features'":[64],"classes.":[67],"On":[68],"other":[70],"hand,":[71],"features":[73,86,109],"play":[74],"roles":[76],"delivering":[78],"content":[80],"of":[81,99,119,147],"document.":[83],"The":[84],"chosen":[85],"expected":[88],"important":[92],"ones,":[93],"carry":[95],"main":[97],"information":[98],"document":[101,122,133],"collection.":[102],"traditional":[105],"considers":[108],"equally":[110],"important.":[111],"To":[112],"overcome":[113],"simultaneously":[114],"above":[116],"two":[117,139],"problems":[118],"frequency":[123,134],"metric,":[124],"we":[125],"propose":[126],"based":[129],"importance":[131],"weighted":[132],"measure.":[135],"Preliminary":[136],"experiments":[137],"on":[138],"classification":[141],"datasets":[142],"do":[143],"validate":[144],"effectiveness":[146],"proposed":[149],"metric.":[150]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}