{"id":"https://openalex.org/W2130681206","doi":"https://doi.org/10.1093/comjnl/bxq069","title":"A Self-enriching Methodology for Clustering Narrow Domain Short Texts","display_name":"A Self-enriching Methodology for Clustering Narrow Domain Short Texts","publication_year":2010,"publication_date":"2010-09-13","ids":{"openalex":"https://openalex.org/W2130681206","doi":"https://doi.org/10.1093/comjnl/bxq069","mag":"2130681206"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxq069","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxq069","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10251/30421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016612157","display_name":"David Pinto","orcid":"https://orcid.org/0000-0002-8516-5925"},"institutions":[{"id":"https://openalex.org/I721619","display_name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla","ror":"https://ror.org/03p2z7827","country_code":"MX","type":"education","lineage":["https://openalex.org/I721619"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"D. Pinto","raw_affiliation_strings":["Faculty of Computer Science, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico","Faculty of Computer Science, Benem\u00e9rita Universidad Auton\u00f3ma de Puebla, Puebla, Mexico"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico","institution_ids":["https://openalex.org/I721619"]},{"raw_affiliation_string":"Faculty of Computer Science, Benem\u00e9rita Universidad Auton\u00f3ma de Puebla, Puebla, Mexico","institution_ids":["https://openalex.org/I721619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053947754","display_name":"Paolo Rosso","orcid":"https://orcid.org/0000-0002-8922-1242"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"P. Rosso","raw_affiliation_strings":["Natural Language Engineering Lab., ELiRF, Universidad Polit\u00e9cnica de Valencia, Valencia, Spain","Natural Language Engineering Lab, ELiRF, Universidad Polit\u00e9cnica de Valencia, Valencia, Spain#TAB#"],"affiliations":[{"raw_affiliation_string":"Natural Language Engineering Lab., ELiRF, Universidad Polit\u00e9cnica de Valencia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]},{"raw_affiliation_string":"Natural Language Engineering Lab, ELiRF, Universidad Polit\u00e9cnica de Valencia, Valencia, Spain#TAB#","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056716721","display_name":"H\u00e9ctor Jim\u00e9nez-Salazar","orcid":null},"institutions":[{"id":"https://openalex.org/I200362191","display_name":"Universidad Aut\u00f3noma Metropolitana","ror":"https://ror.org/02kta5139","country_code":"MX","type":"education","lineage":["https://openalex.org/I200362191"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"H. Jimenez-Salazar","raw_affiliation_strings":["Information Technologies Dept., Universidad Aut\u00f3noma Metropolitana, Mexico city, Mexico"],"affiliations":[{"raw_affiliation_string":"Information Technologies Dept., Universidad Aut\u00f3noma Metropolitana, Mexico city, Mexico","institution_ids":["https://openalex.org/I200362191"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016612157"],"corresponding_institution_ids":["https://openalex.org/I721619"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":4.9615,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95163954,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"54","issue":"7","first_page":"1148","last_page":"1165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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/library-science","display_name":"Library science","score":0.41973042488098145},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4165794551372528},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4160749614238739},{"id":"https://openalex.org/keywords/art-history","display_name":"Art history","score":0.39155182242393494},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.3671661615371704},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.35468339920043945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.32818180322647095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23967820405960083},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0655861496925354}],"concepts":[{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.41973042488098145},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4165794551372528},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4160749614238739},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.39155182242393494},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.3671661615371704},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.35468339920043945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32818180322647095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23967820405960083},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0655861496925354},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/comjnl/bxq069","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxq069","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},{"id":"pmh:oai:riunet.upv.es:10251/30421","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/30421","pdf_url":null,"source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:riunet.upv.es:10251/30421","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/30421","pdf_url":null,"source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313559","display_name":"CERN","ror":"https://ror.org/01ggx4157"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W80619934","https://openalex.org/W137112649","https://openalex.org/W235857814","https://openalex.org/W1494946869","https://openalex.org/W1502904630","https://openalex.org/W1505918596","https://openalex.org/W1519573080","https://openalex.org/W1524966505","https://openalex.org/W1541945783","https://openalex.org/W1574901103","https://openalex.org/W1580638181","https://openalex.org/W1606247040","https://openalex.org/W1631405315","https://openalex.org/W1651093245","https://openalex.org/W1668465360","https://openalex.org/W1765927794","https://openalex.org/W1816845817","https://openalex.org/W1966812932","https://openalex.org/W1967712865","https://openalex.org/W1970974276","https://openalex.org/W1982024311","https://openalex.org/W1985514943","https://openalex.org/W2020936269","https://openalex.org/W2031577530","https://openalex.org/W2038721957","https://openalex.org/W2041565863","https://openalex.org/W2048328704","https://openalex.org/W2052466360","https://openalex.org/W2074449313","https://openalex.org/W2079656678","https://openalex.org/W2088314245","https://openalex.org/W2093390569","https://openalex.org/W2097057650","https://openalex.org/W2098162425","https://openalex.org/W2100074460","https://openalex.org/W2109664771","https://openalex.org/W2113952190","https://openalex.org/W2113952909","https://openalex.org/W2118020653","https://openalex.org/W2121227244","https://openalex.org/W2121401728","https://openalex.org/W2133517430","https://openalex.org/W2138903626","https://openalex.org/W2141128179","https://openalex.org/W2152083411","https://openalex.org/W2155194165","https://openalex.org/W2158830928","https://openalex.org/W2166707169","https://openalex.org/W2408647707","https://openalex.org/W2797177778","https://openalex.org/W2882319491"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W3193615524"],"abstract_inverted_index":{"Clustering":[0],"narrow":[1,41],"domain":[2,124],"short":[3,31],"texts":[4],"is":[5,48],"considered":[6],"to":[7,20,40,49,75,139,174],"be":[8,21,76,167],"a":[9,51,105,155,181],"complex":[10],"task":[11],"because":[12],"of":[13,17,27,45,59,66,107,129],"the":[14,18,24,35,57,91,127,141,176],"intrinsic":[15],"features":[16,178],"corpus":[19,117],"clustered:":[22],"(i)":[23],"low":[25],"frequencies":[26],"vocabulary":[28,37],"terms":[29,81],"in":[30,144,154,172],"texts,":[32],"and":[33,109,123],"(ii)":[34],"high":[36],"overlapping":[38],"associated":[39,179],"domains.":[42],"The":[43],"aim":[44],"this":[46,67,145],"paper":[47],"introduce":[50],"self-term":[52],"expansion":[53],"methodology":[54,70,142],"for":[55,114],"improving":[56],"performance":[58],"clustering":[60],"methods":[61],"when":[62],"dealing":[63],"with":[64,180],"corpora":[65],"kind.":[68],"This":[69],"allows":[71],"raw":[72],"textual":[73,183],"data":[74,94],"enriched":[77],"by":[78,169],"adding":[79],"co-related":[80],"from":[82,90,98],"an":[83,99],"automatically":[84],"constructed":[85],"lexical":[86],"knowledge":[87],"resource":[88],"obtained":[89],"same":[92],"target":[93],"set":[95,106],"(and":[96],"not":[97,138],"external":[100],"resource).":[101],"We":[102],"also":[103],"propose":[104],"supervised":[108],"unsupervised":[110],"text":[111],"assessment":[112,152],"measures":[113,153],"evaluating":[115],"different":[116,177],"features,":[118],"such":[119],"as":[120],"shortness,":[121],"stylometry":[122],"broadness.":[125],"With":[126],"help":[128],"these":[130,151],"measures,":[131],"we":[132,148],"may":[133,166],"determine":[134],"beforehand":[135],"whether":[136],"or":[137],"use":[140],"proposed":[143],"paper.":[146],"Finally,":[147],"integrate":[149],"all":[150],"freely":[156],"available":[157],"web-based":[158],"system":[159],"named":[160],"Watermarking":[161],"Corpora":[162],"On-line":[163],"System,":[164],"which":[165],"used":[168],"computer":[170],"scientists":[171],"order":[173],"evaluate":[175],"given":[182],"corpus.":[184]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
