{"id":"https://openalex.org/W2121293964","doi":"https://doi.org/10.1145/1458502.1458510","title":"A comparison of techniques for estimating IDF values to generate lexical signatures for the web","display_name":"A comparison of techniques for estimating IDF values to generate lexical signatures for the web","publication_year":2008,"publication_date":"2008-10-30","ids":{"openalex":"https://openalex.org/W2121293964","doi":"https://doi.org/10.1145/1458502.1458510","mag":"2121293964"},"language":"en","primary_location":{"id":"doi:10.1145/1458502.1458510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458502.1458510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM workshop on Web information and data management","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/A5073828706","display_name":"Martin Klein","orcid":"https://orcid.org/0000-0003-0130-2097"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Klein","raw_affiliation_strings":["Old Dominion University, Norfolk, VA, USA","Old Dominion University, Norfolk , VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Old Dominion University, Norfolk, VA, USA","institution_ids":["https://openalex.org/I81365321"]},{"raw_affiliation_string":"Old Dominion University, Norfolk , VA, USA","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081811192","display_name":"Michael L. Nelson","orcid":"https://orcid.org/0000-0003-3749-8116"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Nelson","raw_affiliation_strings":["Old Dominion University, Norfolk, VA, USA","Old Dominion University, Norfolk , VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Old Dominion University, Norfolk, VA, USA","institution_ids":["https://openalex.org/I81365321"]},{"raw_affiliation_string":"Old Dominion University, Norfolk , VA, USA","institution_ids":["https://openalex.org/I81365321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.5085,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.97894195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9941999912261963,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9840999841690063,"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":0.8664757013320923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7441132068634033},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6160241961479187},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5249372124671936},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5062624216079712},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.4941876232624054},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42394939064979553},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4011348783969879},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.224427729845047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1265217661857605}],"concepts":[{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.8664757013320923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7441132068634033},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6160241961479187},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5249372124671936},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5062624216079712},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.4941876232624054},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42394939064979553},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4011348783969879},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.224427729845047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1265217661857605},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1458502.1458510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458502.1458510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.4537","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.4537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.odu.edu/~mklein/publications/widm2008-estimate_idf.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.219.6960","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.219.6960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.odu.edu/~mln/pubs/widm-2008/widm-2008.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1492368137","https://openalex.org/W1509991416","https://openalex.org/W1511643356","https://openalex.org/W1518577300","https://openalex.org/W1523813253","https://openalex.org/W1543116020","https://openalex.org/W1622499492","https://openalex.org/W1733633583","https://openalex.org/W1985004975","https://openalex.org/W2027752285","https://openalex.org/W2028014545","https://openalex.org/W2029203225","https://openalex.org/W2041385169","https://openalex.org/W2042676911","https://openalex.org/W2057767944","https://openalex.org/W2117629987","https://openalex.org/W2124416056","https://openalex.org/W2131006463","https://openalex.org/W2136016364","https://openalex.org/W2146223937","https://openalex.org/W2150953676","https://openalex.org/W2153180170","https://openalex.org/W2618567416","https://openalex.org/W4299301436"],"related_works":["https://openalex.org/W1535813599","https://openalex.org/W2025252807","https://openalex.org/W4297883370","https://openalex.org/W2980701895","https://openalex.org/W2121293964","https://openalex.org/W3118323771","https://openalex.org/W2096699795","https://openalex.org/W2111227719","https://openalex.org/W1923577452","https://openalex.org/W1974228362"],"abstract_inverted_index":{"For":[0],"bounded":[1],"datasets":[2],"such":[3,61],"as":[4,106],"the":[5,9,31,98,103,130,139,150,167,170,174,198,220],"TREC":[6],"Web":[7],"Track":[8],"computation":[10],"of":[11,54,75,82,126,136,162,169,185],"term":[12,160],"frequency":[13,18],"(TF)":[14],"and":[15,109,129,142,173,197],"inverse":[16],"document":[17,132,155],"(IDF)":[19],"is":[20,87,194,205],"not":[21],"difficult.":[22],"However,":[23],"since":[24],"IDF":[25,45,67,80,114,230],"cannot":[26],"be":[27,36],"directly":[28],"calculated":[29],"for":[30,59,154,227,232],"entire":[32],"web,":[33],"it":[34,111,208],"must":[35],"estimated.":[37],"We":[38,101,157,176],"see":[39],"a":[40,64,72,99,122,146,159,179],"need":[41],"to":[42,47,78,88,97,148,164,219],"estimate":[43,79],"accurate":[44,91,229],"values":[46,81,231],"generate":[48],"TF-IDF":[49,186],"based":[50,119],"lexical":[51],"signatures":[52],"(LSs)":[53],"web":[55,83,152,233],"pages.":[56,84,234],"Future":[57],"applications":[58],"generating":[60],"LSs":[62],"require":[63],"real":[65],"time":[66],"computation.":[68],"Therefore":[69],"we":[70],"conducted":[71],"comparison":[73],"study":[74],"different":[76],"methods":[77,94,172,224],"Our":[85],"objective":[86],"investigate":[89],"how":[90],"these":[92],"estimation":[93,115],"are":[95,118,225],"compared":[96],"baseline.":[100,175],"use":[102],"Google":[104,151],"N-grams":[105],"our":[107,190],"baseline":[108],"compare":[110],"against":[112],"two":[113,171],"techniques":[116],"which":[117],"on:":[120],"1)":[121],"\"local":[123],"universe\"":[124],"consisting":[125],"textual":[127],"content":[128],"according":[131],"frequencies":[133],"from":[134,138],"copies":[135],"URLs":[137],"Internet":[140],"Archive":[141],"2)":[143],"\"screen":[144],"scraping\",":[145],"technique":[147],"query":[149],"interface":[153],"frequencies.":[156],"found":[158],"overlap":[161],"70":[163],"80%":[165],"between":[166,189],"results":[168,216],"further":[177],"discovered":[178],"great":[180],"agreement":[181],"in":[182,202],"rank":[183],"correlation":[184],"ranked":[187],"terms":[188],"methods.":[191],"Kendall":[192],"\u03c4":[193],"approximately":[195],"0.8":[196],"M-Score":[199],"(penalizing":[200],"discordances":[201],"higher":[203],"ranks)":[204],"even":[206],"higher,":[207],"peaks":[209],"at":[210],"well":[211],"above":[212],"0.9.":[213],"These":[214],"preliminary":[215],"lead":[217],"us":[218],"conclusion":[221],"that":[222],"both":[223],"appropriate":[226],"creating":[228]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}