{"id":"https://openalex.org/W2152682068","doi":"https://doi.org/10.1145/1645953.1646291","title":"Improving binary classification on text problems using differential word features","display_name":"Improving binary classification on text problems using differential word features","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2152682068","doi":"https://doi.org/10.1145/1645953.1646291","mag":"2152682068"},"language":"en","primary_location":{"id":"doi:10.1145/1645953.1646291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/m2vq2sf36","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050280503","display_name":"Justin Martineau","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Justin Martineau","raw_affiliation_strings":["University of Maryland - Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland - Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009972149","display_name":"Tim Finin","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Finin","raw_affiliation_strings":["University of Maryland - Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland - Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020975010","display_name":"Anupam Joshi","orcid":"https://orcid.org/0000-0002-8641-3193"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anupam Joshi","raw_affiliation_strings":["University of Maryland - Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland - Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078654620","display_name":"Shamit Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shamit Patel","raw_affiliation_strings":["University of Maryland - Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland - Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050280503"],"corresponding_institution_ids":["https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":3.0532,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9223303,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2019","last_page":"2024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991000294685364,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991000294685364,"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":0.9987000226974487,"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":0.9976999759674072,"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":0.7227624654769897},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6566470861434937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5859891772270203},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5798607468605042},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5427489876747131},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.46133553981781006},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4286876320838928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35242289304733276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.328222393989563},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.22824886441230774},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.1998765766620636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18819966912269592},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08406960964202881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227624654769897},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6566470861434937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5859891772270203},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5798607468605042},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5427489876747131},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.46133553981781006},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4286876320838928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35242289304733276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.328222393989563},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.22824886441230774},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.1998765766620636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18819966912269592},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08406960964202881},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1645953.1646291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:mdsoar.org:11603/12003","is_oa":false,"landing_page_url":"http://hdl.handle.net/11603/12003","pdf_url":null,"source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"doi:10.13016/m2vq2sf36","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2vq2sf36","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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"}],"best_oa_location":{"id":"doi:10.13016/m2vq2sf36","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2vq2sf36","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1493036841","https://openalex.org/W1574862351","https://openalex.org/W1964613733","https://openalex.org/W1967807490","https://openalex.org/W2114524997","https://openalex.org/W2135731857","https://openalex.org/W2149684865","https://openalex.org/W2166706824"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W1508636238","https://openalex.org/W2112343299","https://openalex.org/W2345184372","https://openalex.org/W1964805666","https://openalex.org/W2386468718","https://openalex.org/W2348964713","https://openalex.org/W2120702419","https://openalex.org/W2970229296","https://openalex.org/W2159269362"],"abstract_inverted_index":{"We":[0,127],"describe":[1],"an":[2,68,129],"efficient":[3],"technique":[4,89,121],"to":[5,48,55,93,141],"weigh":[6],"word-based":[7],"features":[8,42],"in":[9,80],"binary":[10],"classification":[11,19,30,114],"tasks":[12],"and":[13,37,43,72,83,124,136,144],"show":[14,118],"that":[15,119],"it":[16,95,138],"significantly":[17],"improves":[18],"accuracy":[20],"on":[21,110],"a":[22,33,97,111],"range":[23,112],"of":[24,67,75,113,131],"problems.":[25,145],"The":[26],"most":[27],"common":[28],"text":[29],"approach":[31,60,134],"uses":[32,61],"document's":[34],"ngrams":[35],"(words":[36],"short":[38],"phrases)":[39],"as":[40,64],"its":[41,76],"assigns":[44],"feature":[45],"values":[46,62],"equal":[47],"their":[49],"frequency":[50,71],"or":[51],"TFIDF":[52],"score":[53],"relative":[54],"the":[56,65,73,81,102,133],"training":[57,85],"corpus.":[58],"Our":[59,116],"computed":[63],"product":[66],"ngram's":[69],"document":[70,78],"difference":[74],"inverse":[77],"frequencies":[79],"positive":[82],"negative":[84],"sets.":[86],"While":[87],"this":[88],"is":[90,122],"remarkably":[91],"easy":[92],"implement,":[94],"gives":[96],"statistically":[98],"significant":[99],"improvement":[100],"over":[101],"standard":[103],"bag-of-words":[104],"approaches":[105],"using":[106],"support":[107],"vector":[108],"machines":[109],"tasks.":[115],"results":[117],"our":[120],"robust":[123],"broadly":[125],"applicable.":[126],"provide":[128],"analysis":[130],"why":[132],"works":[135],"how":[137],"can":[139],"generalize":[140],"other":[142],"domains":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}