{"id":"https://openalex.org/W7099242551","doi":null,"title":"Entropy of Search Logs: How Hard is Search? With Personalization? With Backoff?","display_name":"Entropy of Search Logs: How Hard is Search? With Personalization? With Backoff?","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W7099242551"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.130.879","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sifaka.cs.uiuc.edu/~qmei2/pub/wsdm08-entropy.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5048955398","display_name":"Qiaozhu Mei","orcid":"https://orcid.org/0000-0002-8640-1942","observed_orcids":["https://orcid.org/0000-0002-8640-1942"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiaozhu Mei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016543371","display_name":"Kenneth Church","orcid":"https://orcid.org/0000-0001-8378-6069","observed_orcids":["https://orcid.org/0000-0001-8378-6069"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenneth Church","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7821637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9994999766349792,"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":0.9994999766349792,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.00019999999494757503,"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/T12016","display_name":"Web Data Mining and Analysis","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/search-logs","display_name":"search logs","score":0.6859999895095825},{"id":"https://openalex.org/keywords/entropy-estimation","display_name":"entropy estimation","score":0.8889999985694885},{"id":"https://openalex.org/keywords/perplexity","display_name":"perplexity","score":0.9549999833106995},{"id":"https://openalex.org/keywords/web-search","display_name":"web search","score":0.4099999964237213},{"id":"https://openalex.org/keywords/personalization","display_name":"personalization","score":0.6740000247955322},{"id":"https://openalex.org/keywords/query-suggestion","display_name":"query suggestion","score":0.875},{"id":"https://openalex.org/keywords/language-modeling","display_name":"language modeling","score":0.6650000214576721},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085000276565552},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.4797999858856201},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C2776945383","wikidata":"https://www.wikidata.org/wiki/Q7170667","display_name":"Personalized search","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C127722929","wikidata":"https://www.wikidata.org/wiki/Q7833714","display_name":"Transaction data","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.130.879","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sifaka.cs.uiuc.edu/~qmei2/pub/wsdm08-entropy.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.146.2748","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.146.2748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/~nenkova/Courses/cis430/p45-mei.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7099161119","https://openalex.org/W2133909581","https://openalex.org/W2152796904","https://openalex.org/W3140643837","https://openalex.org/W2116655434","https://openalex.org/W2077804538","https://openalex.org/W2062918108","https://openalex.org/W2168717408","https://openalex.org/W3135367246","https://openalex.org/W7095259996"],"abstract_inverted_index":{"How":[0,68,72,80],"many":[1],"pages":[2],"are":[3,41,74,171],"there":[4],"on":[5,14],"the":[6,17,36,101,154,159],"Web?":[7],"5B?":[8],"20B?":[9],"More?":[10],"Less?":[11],"Big":[12],"bets":[13],"clusters":[15],"in":[16],"clouds":[18],"could":[19,32],"be":[20,90,180],"wiped":[21],"out":[22],"if":[23,134],"a":[24,28,60,111,126,148],"small":[25],"cache":[26],"of":[27,35,94,144,150,158,167],"few":[29,156],"million":[30],"urls":[31],"capture":[33],"much":[34,81],"value.":[37],"Language":[38],"modeling":[39],"techniques":[40],"applied":[42],"to":[43,47,114,139,162],"MSN\u2019s":[44],"search":[45,97],"logs":[46],"estimate":[48],"entropy.":[49],"The":[50,165],"perplexity":[51],"is":[52,59,70,100],"surprisingly":[53],"small:":[54],"millions,":[55],"not":[56],"billions.":[57],"Entropy":[58],"powerful":[61],"tool":[62],"for":[63,104,125],"sizing":[64],"challenges":[65],"and":[66,141,186,192],"opportunities.":[67],"hard":[69,73],"search?":[71],"query":[75],"suggestion":[76],"mechanisms":[77],"like":[78],"auto-complete?":[79],"does":[82],"personalization":[83,117],"help?":[84],"All":[85],"these":[86],"difficult":[87],"questions":[88],"can":[89],"answered":[91],"by":[92,182],"estimation":[93],"entropy":[95],"from":[96],"logs.":[98],"What":[99],"potential":[102],"opportunity":[103],"personalization?":[105],"In":[106],"this":[107],"paper,":[108],"we":[109,121,129,135,152],"propose":[110],"new":[112],"way":[113],"personalize":[115],"search,":[116],"with":[118,173],"backoff.":[119],"If":[120],"have":[122],"relevant":[123],"data":[124],"particular":[127],"user,":[128],"should":[130],"use":[131,153],"it.":[132],"But":[133],"don\u2019t,":[136],"back":[137],"off":[138],"larger":[140,142],"classes":[143,178],"similar":[145],"users.":[146],"As":[147],"proof":[149],"concept,":[151],"first":[155],"bytes":[157],"IP":[160],"address":[161],"define":[163],"classes.":[164],"coefficients":[166],"each":[168],"backoff":[169],"class":[170],"estimated":[172],"an":[174],"EM":[175],"algorithm.":[176],"Ideally,":[177],"would":[179],"defined":[181],"market":[183],"segments,":[184],"demographics":[185],"surrogate":[187],"variables":[188],"such":[189],"as":[190],"time":[191],"geography.":[193]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}