{"id":"https://openalex.org/W2955898947","doi":"https://doi.org/10.1145/3331184.3331395","title":"Information Retrieval Meets Scalable Text Analytics","display_name":"Information Retrieval Meets Scalable Text Analytics","publication_year":2019,"publication_date":"2019-07-18","ids":{"openalex":"https://openalex.org/W2955898947","doi":"https://doi.org/10.1145/3331184.3331395","mag":"2955898947"},"language":"en","primary_location":{"id":"doi:10.1145/3331184.3331395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331184.3331395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd 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/A5000258262","display_name":"Ryan Clancy","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ryan Clancy","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719134","display_name":"Jae-Jun Lee","orcid":"https://orcid.org/0000-0002-1277-5765"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jaejun Lee","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015214956","display_name":"Zeynep Akkalyoncu Yilmaz","orcid":"https://orcid.org/0000-0003-0055-4110"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zeynep Akkalyoncu Yilmaz","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64054655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1313","last_page":"1316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"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/spark","display_name":"SPARK (programming language)","score":0.9139898419380188},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8315314054489136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.782137393951416},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.765089750289917},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.6096787452697754},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.44600972533226013},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42703500390052795},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38186904788017273},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3363744616508484},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08191999793052673},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07847443222999573}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.9139898419380188},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8315314054489136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782137393951416},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.765089750289917},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.6096787452697754},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.44600972533226013},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42703500390052795},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38186904788017273},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3363744616508484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08191999793052673},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07847443222999573},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3331184.3331395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331184.3331395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W38619841","https://openalex.org/W2007901510","https://openalex.org/W2108871129","https://openalex.org/W2123442489","https://openalex.org/W2146027514","https://openalex.org/W2396476612","https://openalex.org/W2406836379","https://openalex.org/W2417800902","https://openalex.org/W2740321901","https://openalex.org/W2798639660","https://openalex.org/W2899154813","https://openalex.org/W2954150730","https://openalex.org/W6601609194"],"related_works":["https://openalex.org/W2958805129","https://openalex.org/W2112667785","https://openalex.org/W2891870102","https://openalex.org/W2436120840","https://openalex.org/W2527695466","https://openalex.org/W3201703729","https://openalex.org/W3007410698","https://openalex.org/W3087592560","https://openalex.org/W2292449291","https://openalex.org/W2727762105","https://openalex.org/W2547742189","https://openalex.org/W2618005357","https://openalex.org/W2941590232","https://openalex.org/W3197450343","https://openalex.org/W1507154116","https://openalex.org/W2514952927","https://openalex.org/W2259857913","https://openalex.org/W2949223857","https://openalex.org/W2946508622","https://openalex.org/W2388496688"],"abstract_inverted_index":{"Despite":[0],"the":[1,42,76],"broad":[2],"adoption":[3],"of":[4,44,78],"both":[5],"Apache":[6,9],"Spark":[7,85],"and":[8,68],"Solr,":[10],"there":[11,33],"is":[12,28,34],"little":[13],"integration":[14],"between":[15],"these":[16],"two":[17],"platforms":[18],"to":[19,86],"support":[20],"scalable,":[21],"end-to-end":[22],"text":[23,51],"analytics.":[24],"We":[25],"believe":[26],"this":[27],"a":[29],"missed":[30],"opportunity,":[31],"as":[32],"substantial":[35],"synergy":[36],"in":[37],"building":[38],"analytical":[39,66],"pipelines":[40],"where":[41],"results":[43],"potentially":[45],"complex":[46],"faceted":[47],"queries":[48],"feed":[49],"downstream":[50],"processing":[52],"components.":[53],"This":[54],"demonstration":[55],"explores":[56],"exactly":[57],"such":[58],"an":[59],"integration:":[60],"we":[61],"evaluate":[62],"performance":[63],"under":[64],"different":[65],"scenarios":[67],"present":[69],"three":[70],"simple":[71],"case":[72],"studies":[73],"that":[74],"illustrate":[75],"range":[77],"possible":[79],"analyses":[80],"enabled":[81],"by":[82],"seamlessly":[83],"connecting":[84],"Solr.":[87]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
