{"id":"https://openalex.org/W1988643420","doi":"https://doi.org/10.1007/s10032-007-0057-x","title":"Finding structure in noisy text: topic classification and unsupervised clustering","display_name":"Finding structure in noisy text: topic classification and unsupervised clustering","publication_year":2007,"publication_date":"2007-12-01","ids":{"openalex":"https://openalex.org/W1988643420","doi":"https://doi.org/10.1007/s10032-007-0057-x","mag":"1988643420"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-007-0057-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10032-007-0057-x","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Document Analysis and Recognition (IJDAR)","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/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Prem Natarajan","raw_affiliation_strings":["BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107484450","display_name":"Rohit Prasad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohit Prasad","raw_affiliation_strings":["BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111556874","display_name":"Krishna Subramanian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishna Subramanian","raw_affiliation_strings":["BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113479110","display_name":"Shirin Saleem","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shirin Saleem","raw_affiliation_strings":["BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076840260","display_name":"Fred Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fred Choi","raw_affiliation_strings":["BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058546855","display_name":"Rich Schwartz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rich Schwartz","raw_affiliation_strings":["BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, Cambridge, MA, 02138, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies, 10 Moulton Street, 02138, Cambridge, MA, USA#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5066184920"],"corresponding_institution_ids":[],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":1.1171,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8522495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":"3-4","first_page":"187","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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":0.9993000030517578,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9972000122070312,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9962000250816345,"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":0.8014582395553589},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6610124707221985},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.642771303653717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.507061243057251},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4601358473300934},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.41126903891563416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36941349506378174},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.351265013217926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34721022844314575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014582395553589},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6610124707221985},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.642771303653717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.507061243057251},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4601358473300934},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.41126903891563416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36941349506378174},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.351265013217926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34721022844314575}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10032-007-0057-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10032-007-0057-x","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W20483661","https://openalex.org/W184703325","https://openalex.org/W1498731359","https://openalex.org/W1520377376","https://openalex.org/W1557757161","https://openalex.org/W1559013041","https://openalex.org/W1564518192","https://openalex.org/W1667165204","https://openalex.org/W1779834323","https://openalex.org/W1965555277","https://openalex.org/W1986864899","https://openalex.org/W2009961094","https://openalex.org/W2043253481","https://openalex.org/W2064580901","https://openalex.org/W2084301790","https://openalex.org/W2105024701","https://openalex.org/W2116413669","https://openalex.org/W2140336868","https://openalex.org/W2145036943","https://openalex.org/W2149684865","https://openalex.org/W2425056032","https://openalex.org/W2622248957"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W4249589822","https://openalex.org/W2103063669","https://openalex.org/W3184921334","https://openalex.org/W4255446307","https://openalex.org/W2033009170","https://openalex.org/W4386895402","https://openalex.org/W3202382261","https://openalex.org/W4362466842","https://openalex.org/W3200375535"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
