{"id":"https://openalex.org/W2136075087","doi":"https://doi.org/10.3115/1220175.1220243","title":"A study on automatically extracted keywords in text categorization","display_name":"A study on automatically extracted keywords in text categorization","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2136075087","doi":"https://doi.org/10.3115/1220175.1220243","mag":"2136075087"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220243","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220243","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220243","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220243","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018342669","display_name":"Anette Hulth","orcid":"https://orcid.org/0000-0002-3132-808X"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Anette Hulth","raw_affiliation_strings":["Uppsala University, Sweden","Uppsala university, Sweden#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University, Sweden","institution_ids":["https://openalex.org/I123387679"]},{"raw_affiliation_string":"Uppsala university, Sweden#TAB#","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050966080","display_name":"Be\u00e1ta Megyesi","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Be\u00e1ta B. Megyesi","raw_affiliation_strings":["Uppsala University, Sweden","Uppsala university, Sweden#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University, Sweden","institution_ids":["https://openalex.org/I123387679"]},{"raw_affiliation_string":"Uppsala university, Sweden#TAB#","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.3929,"has_fulltext":true,"cited_by_count":169,"citation_normalized_percentile":{"value":0.97460299,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T13083","display_name":"Advanced Text Analysis Techniques","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9973999857902527,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9707000255584717,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8346397876739502},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8212720155715942},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.8122377395629883},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6046804785728455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5647343397140503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5320331454277039},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41424545645713806},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3689664304256439}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8346397876739502},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8212720155715942},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.8122377395629883},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6046804785728455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5647343397140503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5320331454277039},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41424545645713806},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3689664304256439},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1220175.1220243","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220243","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220243","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220243","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220243","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220243","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136075087.pdf","grobid_xml":"https://content.openalex.org/works/W2136075087.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W116908793","https://openalex.org/W140312209","https://openalex.org/W1482724717","https://openalex.org/W1525595230","https://openalex.org/W1576520375","https://openalex.org/W1576676390","https://openalex.org/W1596451018","https://openalex.org/W1755193636","https://openalex.org/W1941537533","https://openalex.org/W2005422315","https://openalex.org/W2064418625","https://openalex.org/W2070589943","https://openalex.org/W2082171025","https://openalex.org/W2098162425","https://openalex.org/W2103333826","https://openalex.org/W2103749038","https://openalex.org/W2137005794","https://openalex.org/W2158728425","https://openalex.org/W2170654002","https://openalex.org/W4242063076"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2390698788","https://openalex.org/W2133651098","https://openalex.org/W2078570174","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,24,34],"study":[4],"on":[5,33],"if":[6],"and":[7],"how":[8],"automatically":[9,50],"extracted":[10,51,69],"keywords":[11,81],"can":[12],"be":[13],"used":[14],"to":[15,61,86],"improve":[16],"text":[17,36],"categorization.":[18],"In":[19],"summary":[20],"we":[21],"show":[22],"that":[23,66],"higher":[25,59],"performance":[26],"---":[27,39],"as":[28,70,91,108,110],"measured":[29],"by":[30,57],"micro-averaged":[31],"F-measure":[32],"standard":[35],"categorization":[37],"collection":[38],"is":[40,46,55],"achieved":[41],"when":[42],"the":[43,49,64,80,83,87,99,102],"full-text":[44],"representation":[45],"combined":[47],"with":[48],"keywords.":[52,71],"The":[53],"combination":[54],"obtained":[56],"giving":[58],"weights":[60],"words":[62],"in":[63,78],"full-texts":[65],"are":[67,82],"also":[68,73],"We":[72],"present":[74],"results":[75],"for":[76],"experiments":[77],"which":[79],"only":[84],"input":[85],"categorizer,":[88],"either":[89],"represented":[90],"unigrams":[92,100],"or":[93],"intact.":[94],"Of":[95],"these":[96],"two":[97],"experiments,":[98],"have":[101],"best":[103],"performance,":[104],"although":[105],"neither":[106],"performs":[107],"well":[109],"headlines":[111],"only.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}