{"id":"https://openalex.org/W4385595313","doi":"https://doi.org/10.1145/3573128.3609341","title":"Technology-Assisted Review for Spreadsheets and Noisy Text","display_name":"Technology-Assisted Review for Spreadsheets and Noisy Text","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385595313","doi":"https://doi.org/10.1145/3573128.3609341"},"language":"en","primary_location":{"id":"doi:10.1145/3573128.3609341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573128.3609341","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573128.3609341","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3573128.3609341","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051834432","display_name":"Tom O\u2019Halloran","orcid":"https://orcid.org/0009-0007-3169-9685"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tom O'Halloran","raw_affiliation_strings":["Grant Thornton Ireland"],"affiliations":[{"raw_affiliation_string":"Grant Thornton Ireland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103075480","display_name":"Bronagh McManus","orcid":"https://orcid.org/0009-0009-4535-7584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bronagh McManus","raw_affiliation_strings":["Grant Thornton Ireland"],"affiliations":[{"raw_affiliation_string":"Grant Thornton Ireland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023931257","display_name":"Andrew Harbison","orcid":"https://orcid.org/0009-0001-3131-0744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Harbison","raw_affiliation_strings":["Grant Thornton Ireland"],"affiliations":[{"raw_affiliation_string":"Grant Thornton Ireland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083981495","display_name":"Maura R. Grossman","orcid":"https://orcid.org/0000-0003-2279-4262"},"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":"Maura R. Grossman","raw_affiliation_strings":["University of Waterloo"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","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"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051834432"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54759385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9939000010490417,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9901999831199646,"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":0.7347396612167358},{"id":"https://openalex.org/keywords/tar","display_name":"tar (computing)","score":0.6203631162643433},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.528403639793396},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46499955654144287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45157212018966675},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42399129271507263},{"id":"https://openalex.org/keywords/grossman","display_name":"Grossman","score":0.4156947731971741},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3794536292552948},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35815948247909546},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3373728096485138},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32458049058914185},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10877439379692078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347396612167358},{"id":"https://openalex.org/C192643346","wikidata":"https://www.wikidata.org/wiki/Q283579","display_name":"tar (computing)","level":2,"score":0.6203631162643433},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.528403639793396},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46499955654144287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45157212018966675},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42399129271507263},{"id":"https://openalex.org/C2780596892","wikidata":"https://www.wikidata.org/wiki/Q21493218","display_name":"Grossman","level":2,"score":0.4156947731971741},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3794536292552948},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35815948247909546},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3373728096485138},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32458049058914185},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10877439379692078},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165556158","wikidata":"https://www.wikidata.org/wiki/Q83937","display_name":"Keynesian economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573128.3609341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573128.3609341","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573128.3609341","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3573128.3609341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573128.3609341","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573128.3609341","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385595313.pdf","grobid_xml":"https://content.openalex.org/works/W4385595313.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2029075138","https://openalex.org/W2104290684","https://openalex.org/W2533861448","https://openalex.org/W4297970707"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2357241418","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4205958290"],"abstract_inverted_index":{"In":[0,41],"a":[1,9,15,74],"large-scale":[2],"eDiscovery":[3],"effort,":[4],"human":[5],"assessors":[6],"participated":[7],"in":[8,103],"technology-assisted":[10],"review":[11,28],"(\"TAR\")":[12],"process":[13],"employing":[14],"modified":[16],"version":[17],"of":[18,54,62],"Grossman":[19],"and":[20,31,93,120],"Cormack's":[21],"Continuous":[22],"Active":[23],"Learning\u00ae":[24],"(\"CAL\u00ae\")":[25],"tool":[26],"to":[27,111],"Excel":[29,91],"spreadsheets":[30,92],"poor-quality":[32],"OCR":[33,95],"text":[34],"(defined":[35],"as":[36],"30-50%":[37],"Markov":[38],"error":[39],"rate).":[40],"the":[42,52,60,104],"legal":[43,105],"industry,":[44],"these":[45,108],"documents":[46],"are":[47,58,99],"typically":[48],"considered":[49],"inappropriate":[50],"for":[51,101],"application":[53],"TAR":[55,76,112],"and,":[56],"consequently,":[57],"usually":[59],"subject":[61],"exhaustive":[63],"manual":[64],"review.":[65],"Our":[66,97],"results":[67,89],"assuage":[68],"this":[69],"concern":[70],"by":[71],"showing":[72],"that":[73],"CAL":[75],"process,":[77],"using":[78],"feature":[79],"engineering":[80],"techniques":[81],"adapted":[82],"from":[83],"spam":[84],"filtering,":[85],"can":[86],"achieve":[87],"satisfactory":[88],"on":[90],"noisy":[94],"text.":[96],"findings":[98],"cause":[100],"optimism":[102],"industry---":[106],"adding":[107],"document":[109],"classes":[110],"datasets":[113],"will":[114],"make":[115],"large":[116],"reviews":[117],"more":[118],"manageable":[119],"less":[121],"costly.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}