{"id":"https://openalex.org/W2019306740","doi":"https://doi.org/10.1145/1458082.1458142","title":"Improved query difficulty prediction for the web","display_name":"Improved query difficulty prediction for the web","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2019306740","doi":"https://doi.org/10.1145/1458082.1458142","mag":"2019306740"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge 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/A5084915697","display_name":"Claudia Hauff","orcid":"https://orcid.org/0000-0001-9879-6470"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Claudia Hauff","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060492418","display_name":"Vanessa Murdock","orcid":"https://orcid.org/0000-0003-1682-0081"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Vanessa Murdock","raw_affiliation_strings":["Yahoo! Research - Barcelona, Barcelona, Spain","Yahoo! Research Barcelona, Barcelona, Spain#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research - Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo! Research Barcelona, Barcelona, Spain#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076204770","display_name":"Ricardo Baeza\u2010Yates","orcid":"https://orcid.org/0000-0003-3208-9778"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Ricardo Baeza-Yates","raw_affiliation_strings":["Yahoo! Research - Barcelona, Barcelona, Spain","Yahoo! Research Barcelona, Barcelona, Spain#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research - Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo! Research Barcelona, Barcelona, Spain#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084915697"],"corresponding_institution_ids":["https://openalex.org/I94624287"],"apc_list":null,"apc_paid":null,"fwci":25.3781,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.99436598,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"439","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9976000189781189,"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/T11106","display_name":"Data Management and Algorithms","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.8440439701080322},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.722458004951477},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.7085952758789062},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7026448249816895},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.67213374376297},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.6205744743347168},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5784679651260376},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49036717414855957},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.4778149425983429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440439701080322},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.722458004951477},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.7085952758789062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7026448249816895},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.67213374376297},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.6205744743347168},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5784679651260376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49036717414855957},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.4778149425983429}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1458082.1458142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/60f5e8ef-2330-4844-ad0c-118659933b18","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/60f5e8ef-2330-4844-ad0c-118659933b18","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hauff, C, Murdock, V & Baeza-Yates, R 2008, Improved query difficulty prediction for the web. in CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge mining., 10.1145/1458082.1458142, Association for Computing Machinery, New York, NY, USA, pp. 439-448, 17th ACM Conference on Information and Knowledge Management, CIKM 2008, Napa Valley, California, United States, 26/10/08. https://doi.org/10.1145/1458082.1458142","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:ris.utwente.nl:publications/60f5e8ef-2330-4844-ad0c-118659933b18","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W60779023","https://openalex.org/W1577798322","https://openalex.org/W1602206323","https://openalex.org/W1605510967","https://openalex.org/W1963658069","https://openalex.org/W1964348731","https://openalex.org/W1995173295","https://openalex.org/W2058200372","https://openalex.org/W2079168273","https://openalex.org/W2087408015","https://openalex.org/W2087818911","https://openalex.org/W2093390569","https://openalex.org/W2103569001","https://openalex.org/W2111212948","https://openalex.org/W2136542423","https://openalex.org/W2169213601","https://openalex.org/W2169583766","https://openalex.org/W4206765718","https://openalex.org/W4240913316","https://openalex.org/W4246858749","https://openalex.org/W6602511761"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2026738364","https://openalex.org/W1793997780","https://openalex.org/W2013069866","https://openalex.org/W3125756434","https://openalex.org/W2572349046","https://openalex.org/W2146885082","https://openalex.org/W2392799717","https://openalex.org/W2538384344","https://openalex.org/W3049728138"],"abstract_inverted_index":{"Query":[0],"performance":[1],"prediction":[2,82,116],"aims":[3],"to":[4,40,42,45,52,57,63],"predict":[5],"whether":[6],"a":[7,11,18],"query":[8,47,81,99,108],"will":[9],"have":[10],"high":[12],"average":[13,23],"precision":[14],"given":[15],"retrieval":[16,95],"from":[17,66],"particular":[19],"collection,":[20],"or":[21,62],"low":[22],"precision.":[24],"An":[25],"accurate":[26],"estimator":[27],"of":[28,31,76,78,114],"the":[29,37,59,79,94],"quality":[30],"search":[32,38,55],"engine":[33,39],"results":[34,65],"can":[35],"allow":[36],"decide":[41],"which":[43,50],"queries":[44,51],"apply":[46],"expansion,":[48],"for":[49],"suggest":[53],"alternative":[54],"terms,":[56],"adjust":[58],"sponsored":[60],"results,":[61],"return":[64],"specialized":[67],"collections.":[68,144],"In":[69],"this":[70],"paper":[71],"we":[72,89,125],"present":[73,111],"an":[74,112],"evaluation":[75],"state":[77],"art":[80],"algorithms,":[83],"both":[84],"post-retrieval":[85],"and":[86,88,107,110,129],"pre-retrieval":[87],"analyze":[90],"their":[91],"sensitivity":[92],"towards":[93],"algorithm.":[96],"We":[97],"evaluate":[98],"difficulty":[100],"predictors":[101,135],"over":[102],"three":[103,137],"widely":[104],"different":[105],"collections":[106],"sets":[109],"analysis":[113],"why":[115],"algorithms":[117],"perform":[118],"significantly":[119],"worse":[120],"on":[121,136],"Web":[122,143],"data.":[123],"Finally":[124],"introduce":[126],"Improved":[127],"Clarity,":[128],"demonstrate":[130],"that":[131],"it":[132],"outperforms":[133],"state-of-the-art":[134],"standard":[138],"collections,":[139],"including":[140],"two":[141],"large":[142]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}