{"id":"https://openalex.org/W2144684109","doi":"https://doi.org/10.1007/978-3-642-31830-6_7","title":"Discovery of Novel Term Associations in a Document Collection","display_name":"Discovery of Novel Term Associations in a Document Collection","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2144684109","doi":"https://doi.org/10.1007/978-3-642-31830-6_7","mag":"2144684109"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-31830-6_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-31830-6_7","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-31830-6_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-31830-6_7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076750465","display_name":"Teemu Hyn\u00f6nen","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Teemu Hyn\u00f6nen","raw_affiliation_strings":["Department of Computer Science and HIIT, University of Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and HIIT, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075074611","display_name":"S\u00e9bastien Mahler","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Mahler","raw_affiliation_strings":["Department of Computer Science and HIIT, University of Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and HIIT, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045869840","display_name":"Hannu Toivonen","orcid":"https://orcid.org/0000-0003-1339-8022"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Hannu Toivonen","raw_affiliation_strings":["Department of Computer Science and HIIT, University of Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and HIIT, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076750465"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.9495,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77185032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9947999715805054,"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/tf\u2013idf","display_name":"tf\u2013idf","score":0.8445943593978882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811309278011322},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7907715439796448},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7168217897415161},{"id":"https://openalex.org/keywords/uniqueness","display_name":"Uniqueness","score":0.529687225818634},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5068710446357727},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.500859260559082},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.47521883249282837},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4298785328865051},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36377471685409546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07498535513877869}],"concepts":[{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.8445943593978882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811309278011322},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7907715439796448},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7168217897415161},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.529687225818634},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5068710446357727},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.500859260559082},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.47521883249282837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4298785328865051},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36377471685409546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07498535513877869},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-31830-6_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-31830-6_7","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-31830-6_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:helda.helsinki.fi:10138/37544","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/37544","pdf_url":"http://hdl.handle.net/10138/37544","source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-642-31830-6_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-31830-6_7","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-31830-6_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4232967162","display_name":"Bisociation Networks for Creative Information Discovery","funder_award_id":"211898","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5483342299","display_name":null,"funder_award_id":"FP7-ICT","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5541357959","display_name":null,"funder_award_id":"7th Framework Programme","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G645663373","display_name":null,"funder_award_id":"7th Framework","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6577931256","display_name":null,"funder_award_id":"118653","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320338370","display_name":"FP7 Information and Communication Technologies","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2144684109.pdf","grobid_xml":"https://content.openalex.org/works/W2144684109.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W199949492","https://openalex.org/W1517637414","https://openalex.org/W1529075208","https://openalex.org/W1638133288","https://openalex.org/W1959533457","https://openalex.org/W1974339500","https://openalex.org/W2003970683","https://openalex.org/W2033441600","https://openalex.org/W2098162425","https://openalex.org/W2140887277","https://openalex.org/W2144211451","https://openalex.org/W2146246571","https://openalex.org/W2147152072","https://openalex.org/W2165612380","https://openalex.org/W2165897980","https://openalex.org/W2178876379","https://openalex.org/W2341078838"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W2741781807"],"abstract_inverted_index":{"We":[0,17,151],"propose":[1],"a":[2,12,206],"method":[3,181],"to":[4,46,54,62,99,132,142],"mine":[5],"novel,":[6],"document-specific":[7],"associations":[8,204],"between":[9],"terms":[10,79],"in":[11,83,115],"collection":[13],"of":[14,37,78,92,124,158,194,205],"unstructured":[15],"documents.":[16],"believe":[18],"that":[19,58,80,138,178,186,198],"documents":[20],"are":[21,81,139,188],"often":[22],"best":[23],"described":[24],"by":[25,34,148],"the":[26,35,108,116,125,149,179,202],"relationships":[27,57],"they":[28,187,199],"establish.":[29],"This":[30],"is":[31,53,130],"also":[32],"evidenced":[33],"popularity":[36],"conceptual":[38,64],"maps,":[39,41],"mind":[40],"and":[42,48,118,164,197],"other":[43],"similar":[44],"methodologies":[45],"organize":[47],"summarize":[49],"information.":[50],"Our":[51],"goal":[52],"discover":[55,183],"term":[56,100,102,119,173],"can":[59,182],"be":[60,143],"used":[61],"construct":[63],"maps":[65],"or":[66,146],"so":[67],"called":[68],"BisoNets.":[69],"The":[70,127,175],"model":[71],"we":[72],"propose,":[73],"tpf\u2013idf\u2013tpu,":[74],"looks":[75],"for":[76,107],"pairs":[77,137,193],"associated":[82],"an":[84],"individual":[85],"document.":[86],"It":[87],"considers":[88],"three":[89],"aspects,":[90],"two":[91,156],"which":[93],"have":[94],"been":[95],"generalized":[96],"from":[97,162,190],"tf\u2013idf":[98,195],"pairs:":[101],"pair":[103,120],"frequency":[104,112],"(tpf;":[105],"importance":[106],"document),":[109],"inverse":[110],"document":[111],"(idf;":[113],"uniqueness":[114],"collection),":[117],"uncorrelation":[121],"(tpu;":[122],"independence":[123],"terms).":[126],"last":[128],"component":[129],"needed":[131],"filter":[133],"out":[134],"statistically":[135],"dependent":[136],"not":[140],"likely":[141],"considered":[144],"novel":[145,184],"interesting":[147],"user.":[150],"present":[152],"experimental":[153],"results":[154,176],"on":[155],"collections":[157],"documents:":[159],"one":[160,165],"extracted":[161],"Wikipedia,":[163],"containing":[166],"text":[167],"mining":[168],"articles":[169],"with":[170],"manually":[171],"assigned":[172],"associations.":[174],"indicate":[177],"tpf\u2013idf\u2013tpu":[180],"associations,":[185],"different":[189],"just":[191],"taking":[192],"keywords,":[196],"match":[200],"better":[201],"subjective":[203],"reader.":[207]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}