{"id":"https://openalex.org/W2132868117","doi":"https://doi.org/10.1109/icpr.2008.4761554","title":"Clustering of Short Commercial Documents for the Web","display_name":"Clustering of Short Commercial Documents for the Web","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2132868117","doi":"https://doi.org/10.1109/icpr.2008.4761554","mag":"2132868117"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2008.4761554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2008.4761554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 19th International Conference on Pattern Recognition","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/A5012902099","display_name":"Moreno Carullo","orcid":null},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Moreno Carullo","raw_affiliation_strings":["Dipartimento di Informatica e Comunicazione, Universit\u00e0 degli Studi dell''Insubria, Varese, Italy","Dipt. di Inf. e Comun., Univ. degli Studi dell'Insubria, Varese"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Comunicazione, Universit\u00e0 degli Studi dell''Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]},{"raw_affiliation_string":"Dipt. di Inf. e Comun., Univ. degli Studi dell'Insubria, Varese","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106083233","display_name":"Elisabetta Binaghi","orcid":null},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisabetta Binaghi","raw_affiliation_strings":["Dipartimento di Informatica e Comunicazione, Universit\u00e0 degli Studi dell''Insubria, Varese, Italy","Dipt. di Inf. e Comun., Univ. degli Studi dell'Insubria, Varese"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Comunicazione, Universit\u00e0 degli Studi dell''Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]},{"raw_affiliation_string":"Dipt. di Inf. e Comun., Univ. degli Studi dell'Insubria, Varese","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054778549","display_name":"Ignazio Gallo","orcid":"https://orcid.org/0000-0002-7076-8328"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ignazio Gallo","raw_affiliation_strings":["Dipartimento di Informatica e Comunicazione, Universit\u00e0 degli Studi dell''Insubria, Varese, Italy","Dipt. di Inf. e Comun., Univ. degli Studi dell'Insubria, Varese"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica e Comunicazione, Universit\u00e0 degli Studi dell''Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]},{"raw_affiliation_string":"Dipt. di Inf. e Comun., Univ. degli Studi dell'Insubria, Varese","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032450711","display_name":"Nicola Lamberti","orcid":"https://orcid.org/0000-0001-5763-3069"},"institutions":[{"id":"https://openalex.org/I4210095524","display_name":"Eurix (Italy)","ror":"https://ror.org/00svj0p64","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210095524"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Lamberti","raw_affiliation_strings":["7pixel srl, Binasco, Italy","7pixel srl, Binasco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"7pixel srl, Binasco, Italy","institution_ids":["https://openalex.org/I4210095524"]},{"raw_affiliation_string":"7pixel srl, Binasco","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9970999956130981,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9970999956130981,"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":0.9944000244140625,"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":0.993399977684021,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8537599444389343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7783244848251343},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7004179358482361},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6056179404258728},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.55257648229599},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5443664193153381},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.5150997042655945},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4854770004749298},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4754980504512787},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46722185611724854},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46212267875671387},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.37260374426841736},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.19334036111831665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.188215970993042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12007588148117065},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08458781242370605}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8537599444389343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783244848251343},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7004179358482361},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6056179404258728},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.55257648229599},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5443664193153381},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.5150997042655945},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4854770004749298},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4754980504512787},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46722185611724854},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46212267875671387},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.37260374426841736},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.19334036111831665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.188215970993042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12007588148117065},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08458781242370605},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icpr.2008.4761554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2008.4761554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 19th International Conference on Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.393","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://figment.cse.usf.edu/~sfefilat/data/papers/TuBCT10.6.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.5605","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.5605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dicom.uninsubria.it/~moreno.carullo/pubs/carulloicpr08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.695.7429","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.695.7429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://artelab.dista.uninsubria.it/res/research/papers/2008/2008_carullo_icpr.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W73128518","https://openalex.org/W202113353","https://openalex.org/W1570542661","https://openalex.org/W1651093245","https://openalex.org/W1679913846","https://openalex.org/W1956559956","https://openalex.org/W1977556410","https://openalex.org/W1997841190","https://openalex.org/W2021457058","https://openalex.org/W2049607461","https://openalex.org/W2110546295","https://openalex.org/W2119953525","https://openalex.org/W2127218421","https://openalex.org/W2135508918","https://openalex.org/W2136663225","https://openalex.org/W2137763598","https://openalex.org/W2147152072","https://openalex.org/W2147159144","https://openalex.org/W2325227998","https://openalex.org/W2793363407","https://openalex.org/W4213332169","https://openalex.org/W4285719527","https://openalex.org/W6676346491","https://openalex.org/W6678914141"],"related_works":["https://openalex.org/W4224240199","https://openalex.org/W2185907214","https://openalex.org/W2519801912","https://openalex.org/W4237492828","https://openalex.org/W2130194910","https://openalex.org/W1538791262","https://openalex.org/W2899601636","https://openalex.org/W2992227719","https://openalex.org/W2049508213","https://openalex.org/W2378900857"],"abstract_inverted_index":{"Document":[0],"clustering":[1,48],"techniques":[2,24],"have":[3],"been":[4],"applied":[5],"in":[6,36,70],"several":[7],"areas,":[8],"with":[9,54,86],"the":[10,15,65,71],"Web":[11],"as":[12],"one":[13],"of":[14,34,57,64],"most":[16],"recent":[17],"and":[18,22,26,84],"influent.":[19],"Both":[20],"general-purpose":[21],"text-oriented":[23,58],"exist":[25],"can":[27,51],"be":[28,52],"used":[29],"to":[30],"cluster":[31],"a":[32,55,78],"collection":[33],"documents":[35],"many":[37],"ways.":[38],"In":[39],"this":[40],"work":[41],"we":[42],"propose":[43],"an":[44],"online,":[45],"single-pass":[46],"document":[47],"model":[49,67],"that":[50],"combined":[53],"variety":[56],"similarity":[59],"measures.":[60],"An":[61],"experimental":[62],"evaluation":[63],"proposed":[66],"was":[68],"conducted":[69],"e-commerce":[72],"domain.":[73],"Performances":[74],"were":[75],"measured":[76],"using":[77],"clustering-oriented":[79],"metric":[80],"based":[81],"on":[82],"F-Measure":[83],"compared":[85],"those":[87],"obtained":[88],"by":[89],"other":[90],"well-known":[91],"approaches.":[92]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
