{"id":"https://openalex.org/W1997305228","doi":"https://doi.org/10.1109/nlpke.2010.5587767","title":"Automatic classification of documents by formality","display_name":"Automatic classification of documents by formality","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W1997305228","doi":"https://doi.org/10.1109/nlpke.2010.5587767","mag":"1997305228"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2010.5587767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2010.5587767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","raw_type":"proceedings-article"},"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/A5047335373","display_name":"Fadi Abu Sheikha","orcid":null},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fadi Abu Sheikha","raw_affiliation_strings":["SITE, University of Ottawa, Ottawa, ONT, Canada","University of Ottawa, SITE, 800 King Edward, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SITE, University of Ottawa, Ottawa, ONT, Canada","institution_ids":["https://openalex.org/I153718931"]},{"raw_affiliation_string":"University of Ottawa, SITE, 800 King Edward, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009188443","display_name":"Diana Inkpen","orcid":"https://orcid.org/0000-0002-0202-2444"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Diana Inkpen","raw_affiliation_strings":["SITE, University of Ottawa, Ottawa, ONT, Canada","University of Ottawa, SITE, 800 King Edward, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SITE, University of Ottawa, Ottawa, ONT, Canada","institution_ids":["https://openalex.org/I153718931"]},{"raw_affiliation_string":"University of Ottawa, SITE, 800 King Edward, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I153718931"],"apc_list":null,"apc_paid":null,"fwci":0.5449,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.61991089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.996399998664856,"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":0.996399998664856,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9825000166893005,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/formality","display_name":"Formality","score":0.8007601499557495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7746145129203796},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6778239607810974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5897802710533142},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5739939212799072},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5261630415916443},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5178301930427551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5159024000167847},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4913610517978668},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46090424060821533},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4381333887577057},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4278803765773773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35451292991638184},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08770221471786499}],"concepts":[{"id":"https://openalex.org/C2777159308","wikidata":"https://www.wikidata.org/wiki/Q1757948","display_name":"Formality","level":2,"score":0.8007601499557495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746145129203796},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6778239607810974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5897802710533142},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5739939212799072},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5261630415916443},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5178301930427551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5159024000167847},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4913610517978668},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46090424060821533},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4381333887577057},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4278803765773773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35451292991638184},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08770221471786499},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2010.5587767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2010.5587767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W184746663","https://openalex.org/W1570448133","https://openalex.org/W2072945242","https://openalex.org/W2098181468","https://openalex.org/W2141274067","https://openalex.org/W2145211186","https://openalex.org/W6607522362"],"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/W3125536479","https://openalex.org/W4224262160","https://openalex.org/W3120363735","https://openalex.org/W4214820172","https://openalex.org/W2394323384"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,15,36,69,74,86],"task":[4],"of":[5,18,88],"classifying":[6],"documents":[7,46],"into":[8],"formal":[9],"or":[10],"informal":[11],"style.":[12],"We":[13,39,53,78],"studied":[14],"main":[16],"characteristics":[17],"each":[19,89],"style":[20],"in":[21,82],"order":[22,83],"to":[23,29,67,73,84,91],"choose":[24,68],"features":[25],"that":[26,32,71],"allowed":[27],"us":[28],"train":[30],"classifiers":[31],"can":[33],"distinguish":[34],"between":[35],"two":[37],"styles.":[38],"built":[40],"our":[41,92],"data":[42],"set":[43],"by":[44],"collecting":[45],"for":[47],"both":[48],"styles,":[49],"from":[50],"different":[51],"sources.":[52],"tested":[54],"several":[55],"classification":[56,76],"algorithms,":[57],"namely":[58],"Decision":[59],"Trees,":[60],"Na\u00efve":[61],"Bayes,":[62],"and":[63],"Support":[64],"Vector":[65],"Machines,":[66],"classifier":[70],"leads":[72],"best":[75],"results.":[77],"performed":[79],"attribute":[80],"selection":[81],"determine":[85],"contribution":[87],"feature":[90],"model.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
