{"id":"https://openalex.org/W4236955586","doi":"https://doi.org/10.1002/(sici)1097-4571(199802)49:2<102::aid-asi2>3.0.co;2-5","title":"Clumping properties of content-bearing words","display_name":"Clumping properties of content-bearing words","publication_year":1998,"publication_date":"1998-02-01","ids":{"openalex":"https://openalex.org/W4236955586","doi":"https://doi.org/10.1002/(sici)1097-4571(199802)49:2<102::aid-asi2>3.0.co;2-5"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1097-4571(199802)49:2<102::aid-asi2>3.0.co;2-5","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1097-4571(199802)49:2<102::aid-asi2>3.0.co;2-5","pdf_url":null,"source":{"id":"https://openalex.org/S4210220780","display_name":"Journal of the American Society for Information Science","issn_l":"0002-8231","issn":["0002-8231","1097-4571"],"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","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":"A. Bookstein","raw_affiliation_strings":["Center for Information and Language Studies, University of Chicago, Chicago, IL 60637"],"affiliations":[{"raw_affiliation_string":"Center for Information and Language Studies, University of Chicago, Chicago, IL 60637","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059517520","display_name":"Shmuel T. Klein","orcid":"https://orcid.org/0000-0002-9478-3303"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"S. T. Klein","raw_affiliation_strings":["Department of Mathematics and CS, Bar Ilan University, Ramat-Gan 52900, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and CS, Bar Ilan University, Ramat-Gan 52900, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"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":true,"raw_author_name":"T. Raita","raw_affiliation_strings":["Computer Science Department, University of Turku, 20520 Turku, Finland"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Turku, 20520 Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008265749","https://openalex.org/A5059517520","https://openalex.org/A5090584872"],"corresponding_institution_ids":["https://openalex.org/I40347166","https://openalex.org/I13955877","https://openalex.org/I155660961"],"apc_list":null,"apc_paid":null,"fwci":0.42455481,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75386991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"49","issue":"2","first_page":"102","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9922000169754028,"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":0.9922000169754028,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9901000261306763,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9815999865531921,"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":0.7259153127670288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833618879318237},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.6805376410484314},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6440821290016174},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6058477759361267},{"id":"https://openalex.org/keywords/bearing","display_name":"Bearing (navigation)","score":0.6010565161705017},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5841055512428284},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5489176511764526},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4964156746864319},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4448287785053253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4164823293685913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3208213150501251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17287570238113403},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12951305508613586},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05945053696632385}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7259153127670288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833618879318237},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.6805376410484314},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6440821290016174},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6058477759361267},{"id":"https://openalex.org/C199978012","wikidata":"https://www.wikidata.org/wiki/Q1273815","display_name":"Bearing (navigation)","level":2,"score":0.6010565161705017},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5841055512428284},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5489176511764526},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4964156746864319},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4448287785053253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4164823293685913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3208213150501251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17287570238113403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12951305508613586},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05945053696632385},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/(sici)1097-4571(199802)49:2<102::aid-asi2>3.0.co;2-5","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1097-4571(199802)49:2<102::aid-asi2>3.0.co;2-5","pdf_url":null,"source":{"id":"https://openalex.org/S4210220780","display_name":"Journal of the American Society for Information Science","issn_l":"0002-8231","issn":["0002-8231","1097-4571"],"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","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1482128759","https://openalex.org/W1771000076","https://openalex.org/W1833785989","https://openalex.org/W1982311747","https://openalex.org/W1985697096","https://openalex.org/W2020418493","https://openalex.org/W2024315858","https://openalex.org/W2029185382","https://openalex.org/W2038925774","https://openalex.org/W2753933954","https://openalex.org/W3144372880","https://openalex.org/W4250657383","https://openalex.org/W4310555669","https://openalex.org/W6635192565","https://openalex.org/W6638697285","https://openalex.org/W6658748723","https://openalex.org/W6669417358","https://openalex.org/W6672179081","https://openalex.org/W7021264618"],"related_works":["https://openalex.org/W2035937180","https://openalex.org/W3196220745","https://openalex.org/W2804364458","https://openalex.org/W42295635","https://openalex.org/W1973996291","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2061308401","https://openalex.org/W2330575325"],"abstract_inverted_index":{"Information":[0],"Retrieval":[1],"Systems":[2],"identify":[3],"content":[4],"bearing":[5,57],"words,":[6],"and":[7,44],"possibly":[8],"also":[9,90],"assign":[10],"weights,":[11],"as":[12,51,77],"part":[13],"of":[14,17,37,40,48,54,92],"the":[15,35,46,64],"process":[16],"formulating":[18],"requests.":[19,100],"For":[20],"optimal":[21],"retrieval":[22],"efficiency,":[23],"it":[24,67],"is":[25,61,68,103],"desirable":[26],"that":[27,66],"this":[28],"be":[29,75,91],"done":[30],"automatically.":[31],"This":[32,59],"article":[33],"defines":[34],"notion":[36],"serial":[38],"clustering":[39,50],"words":[41],"in":[42,63,94,99,109],"text,":[43],"explores":[45],"value":[47,93],"such":[49],"an":[52],"indicator":[53],"a":[55,72],"word's":[56],"content.":[58],"approach":[60],"flexible":[62],"sense":[65],"sensitive":[69],"to":[70,97],"context:":[71],"term":[73],"may":[74,89],"assessed":[76],"content-bearing":[78],"within":[79],"one":[80],"collection,":[81],"but":[82],"not":[83],"another.":[84],"Our":[85],"approach,":[86],"being":[87],"numerical,":[88],"assigning":[95],"weights":[96],"terms":[98],"Experimental":[101],"support":[102],"obtained":[104],"from":[105],"natural":[106],"text":[107],"databases":[108],"three":[110],"different":[111],"languages.":[112],"\u00a9":[113],"1998":[114],"John":[115],"Wiley":[116],"&":[117],"Sons,":[118],"Inc.":[119]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
