{"id":"https://openalex.org/W2460936583","doi":"https://doi.org/10.1145/2911451.2914709","title":"Impact of Review-Set Selection on Human Assessment for Text Classification","display_name":"Impact of Review-Set Selection on Human Assessment for Text Classification","publication_year":2016,"publication_date":"2016-07-07","ids":{"openalex":"https://openalex.org/W2460936583","doi":"https://doi.org/10.1145/2911451.2914709","mag":"2460936583"},"language":"en","primary_location":{"id":"doi:10.1145/2911451.2914709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2911451.2914709","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2914709&type=pdf","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2914709&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048499958","display_name":"Adam Roegiest","orcid":"https://orcid.org/0000-0003-1265-8881"},"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":"Adam Roegiest","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/A5084091807","display_name":"Gordon V. Cormack","orcid":"https://orcid.org/0000-0002-5890-0293"},"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":"Gordon V. Cormack","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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"861","last_page":"864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9962999820709229,"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/selection","display_name":"Selection (genetic algorithm)","score":0.7243658304214478},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7065613269805908},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.67994225025177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6503193378448486},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6427859663963318},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6301067471504211},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.489460825920105},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42661482095718384},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.38791972398757935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37805405259132385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3526532053947449},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20643937587738037}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7243658304214478},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7065613269805908},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.67994225025177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503193378448486},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6427859663963318},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6301067471504211},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.489460825920105},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42661482095718384},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.38791972398757935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37805405259132385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3526532053947449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20643937587738037},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2911451.2914709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2911451.2914709","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2914709&type=pdf","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"}],"best_oa_location":{"id":"doi:10.1145/2911451.2914709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2911451.2914709","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2914709&type=pdf","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2460936583.pdf","grobid_xml":"https://content.openalex.org/works/W2460936583.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W36405575","https://openalex.org/W1554394657","https://openalex.org/W1700671489","https://openalex.org/W1964488075","https://openalex.org/W1967160681","https://openalex.org/W1991774506","https://openalex.org/W2029075138","https://openalex.org/W2037377096","https://openalex.org/W2057495142","https://openalex.org/W2065010255","https://openalex.org/W2071446250","https://openalex.org/W2085989833","https://openalex.org/W2094144755","https://openalex.org/W2120308175","https://openalex.org/W2141653139"],"related_works":["https://openalex.org/W12783365","https://openalex.org/W11991885","https://openalex.org/W193554","https://openalex.org/W3884061","https://openalex.org/W1282129","https://openalex.org/W2990258","https://openalex.org/W3939803","https://openalex.org/W7072919","https://openalex.org/W5641948","https://openalex.org/W5447123"],"abstract_inverted_index":{"In":[0],"a":[1,50],"laboratory":[2],"study,":[3],"human":[4],"assessors":[5],"were":[6,19,80],"significantly":[7],"more":[8,81],"likely":[9,82],"to":[10,36,83,114],"judge":[11],"the":[12,24,98],"same":[13],"documents":[14,27,53,79],"as":[15,34],"relevant":[16,56,86],"when":[17,87],"they":[18],"presented":[20],"for":[21,60,119],"assessment":[22],"within":[23,89],"context":[25],"of":[26,52,63],"selected":[28],"using":[29],"random":[30],"or":[31,122],"uncertainty":[32],"sampling,":[33],"compared":[35],"relevance":[37,101],"sampling.":[38],"The":[39],"effect":[40],"is":[41,68,102],"substantial":[42],"and":[43,57,73,104],"significant":[44],"[0.54":[45],"vs.":[46],"0.42,":[47],"p<0.0002]":[48],"across":[49],"population":[51],"including":[54],"both":[55],"non-relevant":[58],"documents,":[59],"several":[61],"definitions":[62],"ground":[64,116],"truth.":[65],"This":[66],"result":[67],"in":[69,110],"accord":[70],"with":[71],"Smucker":[72],"Jethani's":[74],"SIGIR":[75],"2010":[76],"finding":[77],"that":[78,100,105],"be":[84,115],"judged":[85],"assessed":[88],"low-precision":[90],"versus":[91],"high-precision":[92],"ranked":[93],"lists.":[94],"Our":[95],"study":[96],"supports":[97],"notion":[99],"malleable,":[103],"one":[106],"should":[107],"take":[108],"care":[109],"assuming":[111],"any":[112],"labeling":[113],"truth,":[117],"whether":[118],"training,":[120],"tuning,":[121],"evaluating":[123],"text":[124],"classifiers.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}