{"id":"https://openalex.org/W2157530996","doi":"https://doi.org/10.1145/1062745.1062902","title":"Improving text collection selection with coverage and overlap statistics","display_name":"Improving text collection selection with coverage and overlap statistics","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2157530996","doi":"https://doi.org/10.1145/1062745.1062902","mag":"2157530996"},"language":"en","primary_location":{"id":"doi:10.1145/1062745.1062902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web  - WWW '05","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/A5103817714","display_name":"Thomas Hern\u00e1ndez","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas Hernandez","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023323170","display_name":"Subbarao Kambhampati","orcid":"https://orcid.org/0000-0002-9069-0265"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subbarao Kambhampati","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103817714"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":6.8095,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.97419013,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1128","last_page":"1128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9979000091552734,"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/T11478","display_name":"Caching and Content Delivery","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6911460757255554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6613703370094299},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.45868515968322754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34407639503479004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29213500022888184},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16715505719184875}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6911460757255554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6613703370094299},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.45868515968322754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34407639503479004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29213500022888184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16715505719184875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1062745.1062902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web  - WWW '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.2202","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.2202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2005.org/cdrom/docs/p1128.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W54587332","https://openalex.org/W1484413656","https://openalex.org/W1495119745","https://openalex.org/W1508790985","https://openalex.org/W1536700701","https://openalex.org/W1540841176","https://openalex.org/W1596691921","https://openalex.org/W1603224403","https://openalex.org/W1610765524","https://openalex.org/W1660390307","https://openalex.org/W1854214752","https://openalex.org/W1956218947","https://openalex.org/W1964653195","https://openalex.org/W1983305247","https://openalex.org/W1986828474","https://openalex.org/W1992053235","https://openalex.org/W2011039300","https://openalex.org/W2016892599","https://openalex.org/W2038526807","https://openalex.org/W2044523992","https://openalex.org/W2067432306","https://openalex.org/W2073788020","https://openalex.org/W2073853190","https://openalex.org/W2078165184","https://openalex.org/W2086253379","https://openalex.org/W2097359597","https://openalex.org/W2105258824","https://openalex.org/W2128218289","https://openalex.org/W2131006463","https://openalex.org/W2133676034","https://openalex.org/W2143079043","https://openalex.org/W2162495634","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2469626427","https://openalex.org/W2115485936","https://openalex.org/W2119135658","https://openalex.org/W2153015554","https://openalex.org/W2103338134"],"abstract_inverted_index":{"In":[0],"an":[1],"environment":[2],"of":[3,19,44,103,127],"distributed":[4],"text":[5,57],"collections,":[6,58],"the":[7,11,38,42,55,96,100,111,128],"first":[8],"step":[9],"in":[10,110],"information":[12],"retrieval":[13],"process":[14],"is":[15,49],"to":[16,26,36,124],"identify":[17],"which":[18,31,61,81,93],"all":[20],"available":[21,56],"collections":[22],"are":[23],"more":[24,105],"relevant":[25],"a":[27,59,77],"given":[28],"query":[29],"and":[30,85,114,117],"should":[32],"thus":[33],"be":[34,125],"accessed":[35],"answer":[37],"query.":[39],"We":[40,88],"address":[41],"challenge":[43],"collection":[45,78,112,130],"selection":[46,79,131],"when":[47],"there":[48],"full":[50],"or":[51],"partial":[52],"overlap":[53,86],"between":[54],"scenario":[60],"has":[62],"not":[63],"been":[64],"examined":[65],"previously":[66,122],"despite":[67],"its":[68],"real-world":[69],"applications.":[70],"To":[71],"that":[72,95],"end,":[73],"we":[74],"present":[75],"COSCO,":[76],"approach":[80,98],"uses":[82],"collection-specific":[83],"coverage":[84],"statistics.":[87],"describe":[89],"our":[90],"experimental":[91],"results":[92,107],"show":[94],"presented":[97],"displays":[99],"desired":[101],"behavior":[102],"retrieving":[104],"new":[106],"early":[108],"on":[109],"order,":[113],"performs":[115],"consistently":[116],"significantly":[118],"better":[119],"than":[120],"CORI,":[121],"considered":[123],"one":[126],"best":[129],"systems.":[132]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
