{"id":"https://openalex.org/W2953257359","doi":"https://doi.org/10.1145/3292500.3330766","title":"Seasonal-adjustment Based Feature Selection Method for Predicting Epidemic with Large-scale Search Engine Logs","display_name":"Seasonal-adjustment Based Feature Selection Method for Predicting Epidemic with Large-scale Search Engine Logs","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2953257359","doi":"https://doi.org/10.1145/3292500.3330766","mag":"2953257359"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.09727","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Thien Q. Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Thien Q. Tran","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Sakuma","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Sakuma","raw_affiliation_strings":["University of Tsukuba & RIKEN Center for Advanced Intelligence Project, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba & RIKEN Center for Advanced Intelligence Project, Tsukuba, Japan","institution_ids":["https://openalex.org/I4210126580","https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":1.2757,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79883948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2857","last_page":"2866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10167","display_name":"Influenza Virus Research Studies","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9653000235557556,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6848000288009644},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5583999752998352},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.4059000015258789},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.3970000147819519},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3582000136375427}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6848000288009644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6481000185012817},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5523999929428101},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4047999978065491},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C82691427","wikidata":"https://www.wikidata.org/wiki/Q4291856","display_name":"Pattern search","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2727999985218048}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3292500.3330766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.09727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.09727","pdf_url":"https://arxiv.org/pdf/2008.09727","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.09727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.09727","pdf_url":"https://arxiv.org/pdf/2008.09727","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2017337590","https://openalex.org/W2034203008","https://openalex.org/W2122825543","https://openalex.org/W2138122984","https://openalex.org/W2151485425","https://openalex.org/W2160542585","https://openalex.org/W2604591718","https://openalex.org/W2963714038","https://openalex.org/W2998216295","https://openalex.org/W6698219973"],"related_works":[],"abstract_inverted_index":{"Search":[0],"engine":[1,49],"logs":[2,50,125],"have":[3],"a":[4,52,71,118,146,160,188],"great":[5],"potential":[6],"in":[7,36,77,101,224,232,245],"tracking":[8],"and":[9,42,173,176,235],"predicting":[10],"outbreaks":[11,46],"of":[12,23,32,45,62,70,90,109,209,229],"infectious":[13,34,210],"disease.":[14],"More":[15],"precisely,":[16],"one":[17],"can":[18],"use":[19],"the":[20,29,57,63,67,78,88,95,102,106,110,130,217,239],"search":[21,25,48,64,68,72,96,111,124,195,247],"volume":[22,69,97],"some":[24],"terms":[26,196,248],"to":[27,56,83,105,115,151,192,197,253],"predict":[28,198],"infection":[30],"rate":[31],"an":[33],"disease":[35],"nearly":[37],"real-time.":[38],"However,":[39],"conducting":[40],"accurate":[41],"stable":[43],"prediction":[44,132,178,225],"using":[47],"is":[51,114,120,242],"challenging":[53],"task":[54],"due":[55,82,104],"following":[58],"two-way":[59],"instability":[60,154],"characteristics":[61],"logs.":[65],"First,":[66],"term":[73],"may":[74,98],"change":[75,100,108],"irregularly":[76],"short-term,":[79],"for":[80,180,227],"example,":[81],"environmental":[84],"factors":[85],"such":[86,123,128],"as":[87],"amount":[89],"media":[91],"or":[92],"news.":[93],"Second,":[94],"also":[99,185],"long-term":[103],"demographic":[107],"engine.":[112],"That":[113],"say,":[116],"if":[117],"model":[119],"trained":[121],"with":[122,126],"ignoring":[127],"characteristic,":[129],"resulting":[131],"would":[133],"contain":[134],"serious":[135],"mispredictions":[136],"when":[137],"these":[138],"changes":[139],"occur.":[140],"In":[141,156],"this":[142,153],"work,":[143],"we":[144,158],"proposed":[145,218,240],"novel":[147],"feature":[148,189],"selection":[149,190],"method":[150,162,191,219,241],"overcome":[152],"problem.":[155],"particular,":[157],"employ":[159],"seasonal-adjustment":[161],"that":[163,216,249],"decomposes":[164],"each":[165,181,199],"time":[166],"series":[167],"into":[168],"three":[169],"components:":[170],"seasonal,":[171],"trend":[172],"irregular":[174],"component":[175,182],"build":[177],"models":[179],"individually.":[183],"We":[184,201],"carefully":[186],"design":[187],"select":[193],"proper":[194],"component.":[200],"conducted":[202],"comprehensive":[203],"experiments":[204],"on":[205],"ten":[206,230],"different":[207],"kinds":[208],"diseases.":[211,255],"The":[212],"experimental":[213],"results":[214],"show":[215],"outperforms":[220],"all":[221],"comparative":[222],"methods":[223],"accuracy":[226],"seven":[228],"diseases,":[231],"both":[233],"now-casting":[234],"forecasting":[236],"setting.":[237],"Also,":[238],"more":[243],"successful":[244],"selecting":[246],"are":[250],"semantically":[251],"related":[252],"target":[254]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2019-06-27T00:00:00"}