{"id":"https://openalex.org/W1719006806","doi":"https://doi.org/10.1007/11871842_77","title":"Exploiting Extremely Rare Features in Text Categorization","display_name":"Exploiting Extremely Rare Features in Text Categorization","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W1719006806","doi":"https://doi.org/10.1007/11871842_77","mag":"1719006806"},"language":"en","primary_location":{"id":"doi:10.1007/11871842_77","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11871842_77","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":"book-chapter","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/A5024794223","display_name":"P\u00e9ter Sch\u00f6nhofen","orcid":null},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"P\u00e9ter Sch\u00f6nhofen","raw_affiliation_strings":["Informatics Laboratory, Computer and Automation Research Institute, Hungarian Academy of Sciences, Lagymanyosi u 11, H-1111, Budapest"],"affiliations":[{"raw_affiliation_string":"Informatics Laboratory, Computer and Automation Research Institute, Hungarian Academy of Sciences, Lagymanyosi u 11, H-1111, Budapest","institution_ids":["https://openalex.org/I7597260","https://openalex.org/I4210117195"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021452458","display_name":"Andr\u00e1s A. Bencz\u00far","orcid":"https://orcid.org/0000-0002-9392-0986"},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s A. Bencz\u00far","raw_affiliation_strings":["Informatics Laboratory, Computer and Automation Research Institute, Hungarian Academy of Sciences, Lagymanyosi u 11, H-1111, Budapest"],"affiliations":[{"raw_affiliation_string":"Informatics Laboratory, Computer and Automation Research Institute, Hungarian Academy of Sciences, Lagymanyosi u 11, H-1111, Budapest","institution_ids":["https://openalex.org/I7597260","https://openalex.org/I4210117195"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024794223"],"corresponding_institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.3022,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.5857041,"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":"759","last_page":"766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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":0.9980999827384949,"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":0.8431645631790161},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.7855615615844727},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7494902610778809},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6302807331085205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6117287874221802},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5901888608932495},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5842023491859436},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.543808102607727},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.508761465549469},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5003936290740967},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.45289698243141174},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4516555070877075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38845762610435486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431645631790161},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.7855615615844727},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7494902610778809},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6302807331085205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6117287874221802},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5901888608932495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5842023491859436},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.543808102607727},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.508761465549469},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5003936290740967},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.45289698243141174},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4516555070877075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38845762610435486},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/11871842_77","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11871842_77","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":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W22186808","https://openalex.org/W57814663","https://openalex.org/W140312209","https://openalex.org/W1482905452","https://openalex.org/W1533946607","https://openalex.org/W1985697096","https://openalex.org/W2002857471","https://openalex.org/W2025214515","https://openalex.org/W2040241219","https://openalex.org/W2050712820","https://openalex.org/W2079004251","https://openalex.org/W2081580037","https://openalex.org/W2082690166","https://openalex.org/W2111305191","https://openalex.org/W2119721503","https://openalex.org/W2144211451","https://openalex.org/W2145036943","https://openalex.org/W2149684865","https://openalex.org/W2150102617","https://openalex.org/W2165612380","https://openalex.org/W2316904474","https://openalex.org/W2333314533","https://openalex.org/W2435251607","https://openalex.org/W2752885492","https://openalex.org/W3145128584","https://openalex.org/W4252995400"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2035261173","https://openalex.org/W2138922887","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2082678934","https://openalex.org/W2106892947"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}