{"id":"https://openalex.org/W2016392345","doi":"https://doi.org/10.1145/2467696.2467740","title":"Addressing diverse corpora with cluster-based term weighting","display_name":"Addressing diverse corpora with cluster-based term weighting","publication_year":2013,"publication_date":"2013-07-22","ids":{"openalex":"https://openalex.org/W2016392345","doi":"https://doi.org/10.1145/2467696.2467740","mag":"2016392345"},"language":"en","primary_location":{"id":"doi:10.1145/2467696.2467740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2467696.2467740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-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/A5001038669","display_name":"Peter Organisciak","orcid":"https://orcid.org/0000-0002-9058-2280"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peter Organisciak","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA","University of Illinois at Urbana-Champaign, Champaign, IL, USA;"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA;","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001038669"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07434141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","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/weighting","display_name":"Weighting","score":0.9485430717468262},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.8287448287010193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7918286323547363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5596174597740173},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5557924509048462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5188719034194946},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5000307559967041},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43233582377433777},{"id":"https://openalex.org/keywords/span","display_name":"Span (engineering)","score":0.4319758713245392},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0754101574420929},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.059999287128448486}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.9485430717468262},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.8287448287010193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918286323547363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5596174597740173},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5557924509048462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188719034194946},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5000307559967041},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43233582377433777},{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.4319758713245392},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0754101574420929},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.059999287128448486},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2467696.2467740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2467696.2467740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W150756190","https://openalex.org/W2019096529","https://openalex.org/W2043909051","https://openalex.org/W2075006521","https://openalex.org/W2130395434","https://openalex.org/W2144211451","https://openalex.org/W2153252192","https://openalex.org/W2165612380","https://openalex.org/W6669164439"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W2276271130","https://openalex.org/W2367393702"],"abstract_inverted_index":{"Highly":[0],"heterogeneous":[1],"collections":[2],"present":[3],"difficulties":[4],"to":[5,34,57],"term":[6,47],"weighting":[7,48],"models":[8],"that":[9,53],"are":[10,32],"informed":[11],"by":[12],"corpus-level":[13,78],"frequencies.":[14,80],"Collections":[15],"which":[16,30],"span":[17],"multiple":[18],"languages":[19],"or":[20,60],"large":[21],"time":[22],"periods":[23],"do":[24],"not":[25],"provide":[26],"realistic":[27],"statistics":[28],"on":[29],"words":[31],"interesting":[33],"a":[35,40,51],"system.":[36],"This":[37],"paper":[38],"presents":[39],"case":[41],"where":[42],"diverse":[43,68],"corpora":[44],"can":[45],"frustrate":[46],"and":[49],"proposes":[50],"modification":[52,72],"weighs":[54],"documents":[55],"according":[56],"their":[58],"class":[59],"cluster":[61],"within":[62],"the":[63,70,75],"collection.":[64],"In":[65],"cases":[66],"of":[67],"corpora,":[69],"proposed":[71],"better":[73],"represents":[74],"intuitions":[76],"behind":[77],"document":[79]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
