{"id":"https://openalex.org/W2056947815","doi":"https://doi.org/10.1145/2484028.2484156","title":"Assessor disagreement and text classifier accuracy","display_name":"Assessor disagreement and text classifier accuracy","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2056947815","doi":"https://doi.org/10.1145/2484028.2484156","mag":"2056947815"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th 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/A5110722281","display_name":"William Webber","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Webber","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049353068","display_name":"Jeremy Pickens","orcid":"https://orcid.org/0000-0002-4447-035X"},"institutions":[{"id":"https://openalex.org/I4210115878","display_name":"Laboratory Catalyst Systems (United States)","ror":"https://ror.org/02hf1dy84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210115878"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Pickens","raw_affiliation_strings":["Catalyst Repository Systems, Denver, CO, USA"],"affiliations":[{"raw_affiliation_string":"Catalyst Repository Systems, Denver, CO, USA","institution_ids":["https://openalex.org/I4210115878"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110722281"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":4.4481,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94397531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"929","last_page":"932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991999864578247,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991999864578247,"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":0.9952999949455261,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9929999709129333,"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/classifier","display_name":"Classifier (UML)","score":0.731198787689209},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6691188812255859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6601659655570984},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5943751335144043},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5540873408317566},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5283268690109253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5105053186416626},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48037442564964294},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4258868992328644},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40447139739990234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39384347200393677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18568876385688782},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.12503507733345032}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.731198787689209},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6691188812255859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6601659655570984},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5943751335144043},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5540873408317566},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5283268690109253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105053186416626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48037442564964294},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4258868992328644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40447139739990234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39384347200393677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18568876385688782},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.12503507733345032},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2484028.2484156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.9105","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.9105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.umiacs.umd.edu/~wew/papers/wp13sigir.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1549656520","https://openalex.org/W1618905105","https://openalex.org/W2062236692","https://openalex.org/W2114545736","https://openalex.org/W2120308175","https://openalex.org/W2153635508","https://openalex.org/W2561323583","https://openalex.org/W2565695915","https://openalex.org/W3100570787"],"related_works":["https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W202723009","https://openalex.org/W2145955964","https://openalex.org/W2188612292","https://openalex.org/W4206462905","https://openalex.org/W4382934300"],"abstract_inverted_index":{"Text":[0],"classifiers":[1],"are":[2],"frequently":[3],"used":[4],"for":[5,23,110],"high-yield":[6],"retrieval":[7],"from":[8],"large":[9],"corpora,":[10],"such":[11],"as":[12,109],"in":[13,77,97],"e-discovery.":[14],"The":[15],"classifier":[16,58],"is":[17,40],"trained":[18],"by":[19,31,101],"annotating":[20],"example":[21],"documents":[22],"relevance.":[24],"These":[25],"examples":[26],"may,":[27],"however,":[28],"be":[29],"assessed":[30],"people":[32],"other":[33],"than":[34],"those":[35],"whose":[36],"conception":[37],"of":[38],"relevance":[39],"authoritative.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"examine":[46],"the":[47,63,98,106],"impact":[48],"that":[49,68],"disagreement":[50],"between":[51],"actual":[52],"and":[53],"authoritative":[54,64],"assessor":[55],"has":[56],"upon":[57],"effectiveness,":[59],"when":[60],"evaluated":[61],"against":[62],"conception.":[65],"We":[66],"find":[67],"using":[69],"alternative":[70],"assessors":[71],"leads":[72],"to":[73,91,104],"a":[74],"significant":[75],"decrease":[76],"binary":[78],"classification":[79],"quality,":[80],"though":[81],"less":[82],"so":[83],"ranking":[84,87,99],"quality.":[85],"A":[86],"consumer":[88],"would":[89],"have":[90],"go":[92],"on":[93],"average":[94],"25%":[95],"deeper":[96],"produced":[100],"alternative-assessor":[102],"training":[103],"achieve":[105],"same":[107],"yield":[108],"authoritative-assessor":[111],"training.":[112]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}