{"id":"https://openalex.org/W2464885319","doi":"https://doi.org/10.1145/2911451.2914668","title":"SOGOU-2012-CRAWL","display_name":"SOGOU-2012-CRAWL","publication_year":2016,"publication_date":"2016-07-07","ids":{"openalex":"https://openalex.org/W2464885319","doi":"https://doi.org/10.1145/2911451.2914668","mag":"2464885319"},"language":"en","primary_location":{"id":"doi:10.1145/2911451.2914668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911451.2914668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","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/A5005607929","display_name":"Stewart Whiting","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Stewart Whiting","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051420635","display_name":"Omar Alonso","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omar Alonso","raw_affiliation_strings":["Microsoft, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005607929"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.07318319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"709","last_page":"712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.995199978351593,"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":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.8230617046356201},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7535274028778076},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6784873604774475},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.6559715867042542},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6083452701568604},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.5928834676742554},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5421638488769531},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5142154693603516},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.48266175389289856},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.4112507998943329},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3652247190475464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230617046356201},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7535274028778076},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6784873604774475},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.6559715867042542},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6083452701568604},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.5928834676742554},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5421638488769531},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5142154693603516},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.48266175389289856},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4112507998943329},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3652247190475464},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2911451.2914668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911451.2914668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:128502","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/128502/","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1486587593","https://openalex.org/W1511283908","https://openalex.org/W1956885672","https://openalex.org/W1963726077","https://openalex.org/W1982858363","https://openalex.org/W2022122406","https://openalex.org/W2044002869","https://openalex.org/W2091763897","https://openalex.org/W2108280221","https://openalex.org/W2137426349","https://openalex.org/W2168621303","https://openalex.org/W2169557227","https://openalex.org/W2263474855"],"related_works":["https://openalex.org/W2572349046","https://openalex.org/W2096359267","https://openalex.org/W2026738364","https://openalex.org/W3197639690","https://openalex.org/W2124814993","https://openalex.org/W2113390685","https://openalex.org/W2017989738","https://openalex.org/W1981131819","https://openalex.org/W8514837","https://openalex.org/W2186703450"],"abstract_inverted_index":{"In":[0,49,121,158],"2012,":[1],"Sogou,":[2],"a":[3,10,31,37,178],"major":[4],"Chinese":[5,56],"web":[6,23,153,171],"search":[7,25,59,156,207],"engine":[8],"released":[9],"large-scale":[11,95],"query":[12,28,71,96,114,128,194],"log":[13,29,97,129],"containing":[14],"43.5M":[15],"user":[16],"interactions,":[17],"including":[18,113],"submitted":[19,196],"queries":[20,35,188],"and":[21,118,130,134,155,200],"clicked":[22,64,206],"page":[24],"results.":[26,208],"This":[27],"offers":[30,104],"deep":[32],"sample":[33],"of":[34,78,164,187],"over":[36],"two":[38],"day":[39],"period":[40],"from":[41],"30th":[42],"December":[43],"2011":[44],"to":[45,81,138,146,218],"1st":[46],"January":[47],"2012.":[48],"August":[50],"2013,":[51],"we":[52,88,124,142,160,176],"identified":[53],"1.4M":[54],"predominantly":[55],"language":[57],"unique":[58],"result":[60],"URLs":[61,80],"that":[62],"were":[63],"at":[65],"least":[66],"three":[67],"times":[68],"in":[69,90,152,168,204],"this":[70,91,103,122],"log.":[72],"We":[73,209],"crawled":[74,170],"the":[75,83,127,144,162,169,183,191,193,198,201,205],"HTML":[76],"content":[77,154],"these":[79],"construct":[82],"supplementary":[84],"SOGOU-2012-CRAWL":[85],"dataset,":[86],"which":[87,215],"release":[89],"work.":[92],"A":[93],"real":[94],"with":[98],"accompanying":[99],"crawl":[100,131,145],"such":[101],"as":[102],"several":[105,211],"opportunities":[106],"for":[107,181],"reproducible":[108],"information":[109],"retrieval":[110],"(IR)":[111],"research,":[112],"classification,":[115],"intent":[116,186],"modelling":[117,182],"indexing":[119],"strategy.":[120],"paper":[123],"first":[125],"detail":[126],"dataset":[132],"construction":[133],"characteristics.":[135],"Following":[136],"this,":[137,175],"demonstrate":[139],"potential":[140],"applications":[141],"use":[143],"indicatively":[147],"analyse":[148],"various":[149],"time-based":[150],"patterns":[151,214],"behaviour.":[157],"particular,":[159],"study":[161],"distribution":[163],"language-independent":[165],"date":[166,192],"expressions":[167],"content.":[172],"Based":[173],"on":[174,190],"propose":[177],"simple":[179],"approach":[180],"past/present/future":[184],"temporal":[185,213],"based":[189],"was":[195],"by":[197],"user,":[199],"dates":[202],"appearing":[203],"observe":[210],"prominent":[212],"may":[216],"lead":[217],"novel":[219],"time-aware":[220],"IR":[221],"approaches.":[222]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-07-22T00:00:00"}
