{"id":"https://openalex.org/W2053915461","doi":"https://doi.org/10.1109/cip.2010.5604085","title":"Finding surprising patterns in textual data streams","display_name":"Finding surprising patterns in textual data streams","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2053915461","doi":"https://doi.org/10.1109/cip.2010.5604085","mag":"2053915461"},"language":"en","primary_location":{"id":"doi:10.1109/cip.2010.5604085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cip.2010.5604085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 2nd International Workshop on Cognitive Information Processing","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/A5027344461","display_name":"Tristan Snowsill","orcid":"https://orcid.org/0000-0001-7406-2819"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tristan Snowsill","raw_affiliation_strings":["Intelligent Systems Laboratory, University of Bristol, Bristol, UK","Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038573335","display_name":"Florent Nicart","orcid":"https://orcid.org/0009-0001-2663-4306"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Florent Nicart","raw_affiliation_strings":["Intelligent Systems Laboratory, University of Bristol, Bristol, UK","Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102120030","display_name":"Marco Stefani","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marco Stefani","raw_affiliation_strings":["Intelligent Systems Laboratory, University of Bristol, Bristol, UK","Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076045275","display_name":"Tijl De Bie","orcid":"https://orcid.org/0000-0002-2692-7504"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tijl De Bie","raw_affiliation_strings":["Intelligent Systems Laboratory, University of Bristol, Bristol, UK","Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083307694","display_name":"Nello Cristianini","orcid":"https://orcid.org/0000-0001-7740-0449"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nello Cristianini","raw_affiliation_strings":["Intelligent Systems Laboratory, University of Bristol, Bristol, UK","Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Intelligent Systems Laboratory, University of Bristol, Merchant Venturers Building, BS8 1UB, UK","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":2.7318,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91567332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9966999888420105,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8512427806854248},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.8172807097434998},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.743941068649292},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.6552263498306274},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.550849199295044},{"id":"https://openalex.org/keywords/streams","display_name":"STREAMS","score":0.4729561507701874},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4699167311191559},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.4667789041996002},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44265061616897583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43874362111091614},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3885233402252197},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37029343843460083},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34515270590782166},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3029220700263977},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08627226948738098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8512427806854248},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.8172807097434998},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.743941068649292},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.6552263498306274},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.550849199295044},{"id":"https://openalex.org/C42090638","wikidata":"https://www.wikidata.org/wiki/Q4048907","display_name":"STREAMS","level":2,"score":0.4729561507701874},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4699167311191559},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.4667789041996002},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44265061616897583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43874362111091614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3885233402252197},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37029343843460083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34515270590782166},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3029220700263977},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08627226948738098},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/cip.2010.5604085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cip.2010.5604085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 2nd International Workshop on Cognitive Information Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05068105v1","is_oa":false,"landing_page_url":"https://normandie-univ.hal.science/hal-05068105","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2010 2nd International Workshop on Cognitive Information Processing (CIP), Jun 2010, Elba Island, France. pp.405-410, &#x27E8;10.1109/CIP.2010.5604085&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:archive.ugent.be:7031729","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/7031729","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 978-1-4244-6457-9","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire_cris_publications/9bd44c04-e9be-4f01-8547-7707e5fb2312","is_oa":false,"landing_page_url":"https://hdl.handle.net/1983/9bd44c04-e9be-4f01-8547-7707e5fb2312","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Snowsill, TM, Florent, N, Marco, S, Tijl De, B & Cristianini, N 2010, Finding surprising patterns in textual data streams. in Unknown.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/9bd44c04-e9be-4f01-8547-7707e5fb2312","is_oa":false,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/9bd44c04-e9be-4f01-8547-7707e5fb2312","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Snowsill, TM, Florent, N, Marco, S, Tijl De, B & Cristianini, N 2010, Finding surprising patterns in textual data streams. in Unknown.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G740199657","display_name":null,"funder_award_id":"EP/G056447/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1978394996","https://openalex.org/W1995003166","https://openalex.org/W1998224037","https://openalex.org/W2048927209","https://openalex.org/W2059513841","https://openalex.org/W2064988570","https://openalex.org/W2067981498","https://openalex.org/W2119939946","https://openalex.org/W2121252285","https://openalex.org/W2127492100","https://openalex.org/W2533248932","https://openalex.org/W2613214602","https://openalex.org/W4234917632"],"related_works":["https://openalex.org/W96331545","https://openalex.org/W1548907175","https://openalex.org/W1882920571","https://openalex.org/W2583658747","https://openalex.org/W1517600056","https://openalex.org/W2159942118","https://openalex.org/W2160738675","https://openalex.org/W2036633468","https://openalex.org/W193772702","https://openalex.org/W2003608043"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,18,22,71,88,96,99,143],"task":[3],"of":[4,42,73,75,80,92,98,136],"detecting":[5],"surprising":[6,68],"patterns":[7],"in":[8,17,44,67,70,95,157],"large":[9,90],"textual":[10],"data":[11,23,120],"streams.":[12],"These":[13],"can":[14,109,153],"reveal":[15],"events":[16],"real":[19],"world":[20],"when":[21],"streams":[24,47],"are":[25,60,65],"generated":[26],"by":[27],"online":[28],"news":[29],"media,":[30],"emails,":[31],"Twitter":[32],"feeds,":[33],"movie":[34],"subtitles,":[35],"scientific":[36],"publications,":[37],"and":[38],"more.":[39],"The":[40],"volume":[41],"interest":[43],"such":[45,54],"text":[46],"often":[48],"exceeds":[49],"human":[50],"capacity":[51],"for":[52],"analysis,":[53],"that":[55],"automatic":[56],"pattern":[57],"recognition":[58],"tools":[59],"indispensable.":[61],"In":[62],"particular,":[63],"we":[64,105,116,140],"interested":[66],"changes":[69],"frequency":[72],"n-grams":[74,94],"words,":[76],"or":[77],"more":[78],"generally":[79],"symbols":[81],"from":[82],"an":[83,158],"unlimited":[84],"alphabet":[85,100],"size.":[86],"Despite":[87],"exponentially":[89],"number":[91],"possible":[93],"size":[97],"(which":[101],"is":[102,129],"itself":[103],"unbounded),":[104],"show":[106,141],"how":[107,142],"these":[108,150],"be":[110,155],"detected":[111],"efficiently.":[112],"To":[113],"this":[114],"end,":[115],"rely":[117],"on":[118],"a":[119,124,133],"structure":[121],"known":[122],"as":[123,147,149],"generalised":[125,144],"suffix":[126,145],"tree,":[127],"which":[128],"additionally":[130],"annotated":[131],"with":[132],"limited":[134],"amount":[135],"statistical":[137,151],"information.":[138],"Crucially,":[139],"tree":[146],"well":[148],"annotations":[152],"efficiently":[154],"updated":[156],"on-line":[159],"fashion.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
