{"id":"https://openalex.org/W1740019157","doi":"https://doi.org/10.3233/ica-2008-15405","title":"Utilizing phrase-similarity measures for detecting and clustering informative RSS news articles","display_name":"Utilizing phrase-similarity measures for detecting and clustering informative RSS news articles","publication_year":2008,"publication_date":"2008-07-31","ids":{"openalex":"https://openalex.org/W1740019157","doi":"https://doi.org/10.3233/ica-2008-15405","mag":"1740019157"},"language":"en","primary_location":{"id":"doi:10.3233/ica-2008-15405","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ica-2008-15405","pdf_url":null,"source":{"id":"https://openalex.org/S107631664","display_name":"Integrated Computer-Aided Engineering","issn_l":"1069-2509","issn":["1069-2509","1875-8835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Integrated Computer-Aided Engineering","raw_type":"journal-article"},"type":"article","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/A5064985976","display_name":"Maria Soledad Pera","orcid":"https://orcid.org/0000-0002-2008-9204"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maria Soledad Pera","raw_affiliation_strings":["Computer Science Department, Brigham Young University, Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086456104","display_name":"Yiu\u2010Kai Ng","orcid":"https://orcid.org/0000-0002-5680-2796"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiu-Kai Ng","raw_affiliation_strings":["Computer Science Department, Brigham Young University, Provo, UT, USA","(Correspd. E-mail: ng@cs.byu.edu) Computer Science Department, Brigham Young University, Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]},{"raw_affiliation_string":"(Correspd. E-mail: ng@cs.byu.edu) Computer Science Department, Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064985976"],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":7.6431,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96811626,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":"4","first_page":"331","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9926000237464905,"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/rss","display_name":"RSS","score":0.7863818407058716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507180571556091},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7171285152435303},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6828255653381348},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.6228532195091248},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.5900797247886658},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4632042646408081},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4524369239807129},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43183454871177673},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41202986240386963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37283408641815186},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3286731541156769},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14347538352012634},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09210556745529175},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06106489896774292}],"concepts":[{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.7863818407058716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507180571556091},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7171285152435303},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6828255653381348},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.6228532195091248},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.5900797247886658},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4632042646408081},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4524369239807129},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43183454871177673},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41202986240386963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37283408641815186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3286731541156769},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14347538352012634},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09210556745529175},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06106489896774292},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/ica-2008-15405","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ica-2008-15405","pdf_url":null,"source":{"id":"https://openalex.org/S107631664","display_name":"Integrated Computer-Aided Engineering","issn_l":"1069-2509","issn":["1069-2509","1875-8835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Integrated Computer-Aided Engineering","raw_type":"journal-article"},{"id":"pmh:oai:scholarsarchive.byu.edu:facpub-1947","is_oa":false,"landing_page_url":"https://scholarsarchive.byu.edu/facpub/948","pdf_url":null,"source":{"id":"https://openalex.org/S4377196308","display_name":"ScholarsArchive  (Brigham Young University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100005738","host_organization_name":"Brigham Young University","host_organization_lineage":["https://openalex.org/I100005738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.6125","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.6125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://faculty.cs.byu.edu/~dennis/papers/ClusterRSS.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W181283514","https://openalex.org/W243915216","https://openalex.org/W1517906935","https://openalex.org/W1583833362","https://openalex.org/W1591377317","https://openalex.org/W1592091759","https://openalex.org/W1981081578","https://openalex.org/W1999247496","https://openalex.org/W2006226872","https://openalex.org/W2013029404","https://openalex.org/W2013849299","https://openalex.org/W2019529630","https://openalex.org/W2039346806","https://openalex.org/W2054638878","https://openalex.org/W2064580901","https://openalex.org/W2064742743","https://openalex.org/W2070670538","https://openalex.org/W2072208512","https://openalex.org/W2087447526","https://openalex.org/W2091340087","https://openalex.org/W2098162425","https://openalex.org/W2099111195","https://openalex.org/W2103814434","https://openalex.org/W2119137875","https://openalex.org/W2121947440","https://openalex.org/W2122683551","https://openalex.org/W2133576408","https://openalex.org/W2135170556","https://openalex.org/W2137763598","https://openalex.org/W2139850885","https://openalex.org/W2141751077","https://openalex.org/W2147674242","https://openalex.org/W2150102617","https://openalex.org/W2150791526","https://openalex.org/W2159080219","https://openalex.org/W2162495634","https://openalex.org/W2165607884","https://openalex.org/W2171144767","https://openalex.org/W3144708829"],"related_works":["https://openalex.org/W2011383762","https://openalex.org/W4327499987","https://openalex.org/W2048414027","https://openalex.org/W3173084154","https://openalex.org/W2940857995","https://openalex.org/W2940684586","https://openalex.org/W2809276897","https://openalex.org/W2031891814","https://openalex.org/W353876725","https://openalex.org/W2117086786"],"abstract_inverted_index":{"As":[0],"the":[1,11,18,21],"number":[2,31],"of":[3,20,32,39],"RSS":[4],"news":[5,33],"feeds":[6],"continue":[7],"to":[8,16,27,35],"increase":[9],"over":[10],"Internet,":[12],"it":[13],"becomes":[14],"necessary":[15],"minimize":[17],"workload":[19],"user":[22],"who":[23],"is":[24,42],"otherwise":[25],"required":[26],"scan":[28],"through":[29],"huge":[30],"articles":[34,38],"find":[36],"related":[37],"interest,":[40],"which":[41],"a":[43]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-03T06:03:33.228499","created_date":"2025-10-10T00:00:00"}