{"id":"https://openalex.org/W4241114795","doi":"https://doi.org/10.1002/1532-2890(2001)9999:9999<::aid-asi1088>3.0.co;2-n","title":"Discovering term occurrence structure in text","display_name":"Discovering term occurrence structure in text","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W4241114795","doi":"https://doi.org/10.1002/1532-2890(2001)9999:9999<::aid-asi1088>3.0.co;2-n"},"language":"en","primary_location":{"id":"doi:10.1002/1532-2890(2001)9999:9999<::aid-asi1088>3.0.co;2-n","is_oa":false,"landing_page_url":"https://doi.org/10.1002/1532-2890(2001)9999:9999<::aid-asi1088>3.0.co;2-n","pdf_url":null,"source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","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/A5008265749","display_name":"Abraham Bookstein","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abraham Bookstein","raw_affiliation_strings":["University of Chicago, 1010 E. 59 St., Chicago, IL 60637"],"affiliations":[{"raw_affiliation_string":"University of Chicago, 1010 E. 59 St., Chicago, IL 60637","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090584872","display_name":"T. Raita","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"T. Raita","raw_affiliation_strings":["Comp. Sci. Dept., University of Turku, 20520 Turku, Finland"],"affiliations":[{"raw_affiliation_string":"Comp. Sci. Dept., University of Turku, 20520 Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008265749"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":1.0544,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85165101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"52","issue":"6","first_page":"476","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing 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/T10181","display_name":"Natural Language Processing 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/T11269","display_name":"Algorithms and Data Compression","score":0.9988999962806702,"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":0.9979000091552734,"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/measure","display_name":"Measure (data warehouse)","score":0.7941173315048218},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7150475382804871},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6309019327163696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5986412763595581},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5181983113288879},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43810826539993286},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.411639928817749},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36829009652137756},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3456389307975769},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3228307068347931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3165532946586609},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24919861555099487},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06842130422592163}],"concepts":[{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.7941173315048218},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7150475382804871},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6309019327163696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5986412763595581},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5181983113288879},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43810826539993286},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.411639928817749},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36829009652137756},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3456389307975769},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3228307068347931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3165532946586609},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24919861555099487},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06842130422592163},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/1532-2890(2001)9999:9999<::aid-asi1088>3.0.co;2-n","is_oa":false,"landing_page_url":"https://doi.org/10.1002/1532-2890(2001)9999:9999<::aid-asi1088>3.0.co;2-n","pdf_url":null,"source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W637241713","https://openalex.org/W1559631118","https://openalex.org/W2086348764","https://openalex.org/W6637794560","https://openalex.org/W6639971975","https://openalex.org/W6674877832"],"related_works":["https://openalex.org/W4234874385","https://openalex.org/W2323648130","https://openalex.org/W2157140558","https://openalex.org/W4255837520","https://openalex.org/W2378782423","https://openalex.org/W2387011115","https://openalex.org/W4233308809","https://openalex.org/W2388988621","https://openalex.org/W2357797405","https://openalex.org/W2151762367"],"abstract_inverted_index":{"This":[0],"article":[1],"examines":[2],"some":[3],"consequences":[4],"for":[5,37],"information":[6],"control":[7],"of":[8,11,13,22,34,45,79,88,92],"the":[9,32,50,71,74,80,86,89],"tendency":[10],"occurrences":[12],"content-bearing":[14],"terms":[15],"to":[16,94],"appear":[17],"together,":[18],"or":[19],"clump.":[20],"Properties":[21],"previously":[23],"defined":[24],"clumping":[25,46],"measures":[26,36,52],"are":[27,66],"reviewed":[28],"and":[29,31,61,77],"extended,":[30],"significance":[33],"these":[35],"devising":[38],"retrieval":[39],"strategies":[40],"discussed.":[41],"A":[42],"new":[43,75],"type":[44],"measure,":[47],"which":[48],"extends":[49],"earlier":[51,81],"by":[53],"permitting":[54],"gaps":[55],"within":[56],"a":[57],"clump,":[58],"is":[59],"defined,":[60],"several":[62],"variants":[63],"examined.":[64],"Experiments":[65],"carried":[67],"out":[68],"that":[69],"indicate":[70],"relation":[72],"between":[73],"measure":[76,93],"one":[78],"measures,":[82],"as":[83,85],"well":[84],"ability":[87],"two":[90],"types":[91],"predict":[95],"compression":[96],"efficiency.":[97]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}