{"id":"https://openalex.org/W2003984229","doi":"https://doi.org/10.1145/1146847.1146884","title":"Effective level of term frequency impact on large-scale retrieval performance","display_name":"Effective level of term frequency impact on large-scale retrieval performance","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2003984229","doi":"https://doi.org/10.1145/1146847.1146884","mag":"2003984229"},"language":"en","primary_location":{"id":"doi:10.1145/1146847.1146884","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1146847.1146884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st international conference on Scalable information systems  - InfoScale '06","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/A5012990419","display_name":"Soheila Karbasi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Soheila Karbasi","raw_affiliation_strings":["IRIT-SIG, Campus Univ. Toulouse III, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"IRIT-SIG, Campus Univ. Toulouse III, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052301458","display_name":"Mohand Boughanem","orcid":"https://orcid.org/0000-0001-7004-0807"},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohand Boughanem","raw_affiliation_strings":["IRIT-SIG, Campus Univ. Toulouse III, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"IRIT-SIG, Campus Univ. Toulouse III, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012990419"],"corresponding_institution_ids":["https://openalex.org/I134560555","https://openalex.org/I4210119061"],"apc_list":null,"apc_paid":null,"fwci":0.8208,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82941505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"es"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/term","display_name":"Term (time)","score":0.7961629629135132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6148871183395386},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5415414571762085},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3445625305175781},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1133526861667633},{"id":"https://openalex.org/keywords/astronomy","display_name":"Astronomy","score":0.08264058828353882},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06772005558013916},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06513392925262451}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7961629629135132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6148871183395386},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5415414571762085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3445625305175781},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1133526861667633},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.08264058828353882},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06772005558013916},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06513392925262451}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1146847.1146884","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1146847.1146884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st international conference on Scalable information systems  - InfoScale '06","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1516726196","https://openalex.org/W1554385128","https://openalex.org/W1587004086","https://openalex.org/W1956559956","https://openalex.org/W1974339500","https://openalex.org/W1978394996","https://openalex.org/W1988711048","https://openalex.org/W1994960885","https://openalex.org/W2000569744","https://openalex.org/W2030507931","https://openalex.org/W2061261643","https://openalex.org/W2105380208","https://openalex.org/W2118131693","https://openalex.org/W2134557008","https://openalex.org/W2916923842"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"As":[0],"the":[1,16,28,32,47,58,64,78,93,109,114,123,137,142,153,161,183,190,193,200],"volume":[2],"of":[3,18,31,60,71,88,120,136,145,155,164,182,192],"information":[4,7,195],"increases,":[5],"effective":[6,162],"retrieval":[8,44,65,196],"methods":[9],"become":[10],"more":[11,198],"essential":[12],"to":[13,26,56,77,107,188],"deal":[14],"with":[15],"growth":[17],"information.":[19],"Present":[20],"document":[21,35,94,147],"develops":[22],"a":[23,68,83,132,169],"new":[24],"method":[25,128,186],"assess":[27],"potential":[29],"role":[30],"term":[33,89,165],"frequency-inverse":[34],"frequency":[36,166],"measures":[37],"that":[38,91],"are":[39,148],"commonly":[40],"used":[41,106],"in":[42,67,172,177],"text":[43],"systems":[45,197],"by":[46],"vector":[48,72,202],"space":[49,73,203],"model.":[50,74],"We":[51],"carried":[52],"out":[53],"preliminary":[54,79],"tests":[55],"know":[57],"effect":[59],"term-weighing":[61],"items":[62],"on":[63,97,158],"performance":[66,191],"basic":[69],"scheme":[70],"With":[75],"regard":[76],"tests,":[80],"we":[81],"identify":[82],"novel":[84],"factor":[85,104,171],"(effective":[86],"level":[87,163],"frequency)":[90],"represents":[92],"content":[95],"based":[96],"its":[98],"length":[99],"and":[100,116],"maximum":[101,110],"term-frequency.":[102],"This":[103],"is":[105,168,187],"find":[108],"principal":[111,143],"terms":[112,144],"within":[113],"documents":[115,121],"an":[117],"appropriate":[118],"subset":[119],"containing":[122],"query":[124],"terms.":[125],"Our":[126],"proposed":[127],"(Top-Term":[129],"Ranking)":[130],"uses":[131],"reduced":[133],"indexing":[134],"view":[135],"original":[138],"terms,":[139],"where":[140],"only":[141],"each":[146],"considered":[149],"for":[150],"weighting.":[151],"Regarding":[152],"result":[154],"our":[156],"experiments":[157],"TREC":[159],"collections,":[160],"(EL)":[167],"significant":[170],"retrieving":[173],"relevant":[174],"documents,":[175],"especially":[176],"large":[178],"collections.":[179],"The":[180],"interest":[181],"Top-Term":[184],"Ranking":[185],"increase":[189],"large-scale":[194],"than":[199],"common":[201],"methods.":[204]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
