{"id":"https://openalex.org/W2018924662","doi":"https://doi.org/10.1145/1148170.1148325","title":"The effect of OCR errors on stylistic text classification","display_name":"The effect of OCR errors on stylistic text classification","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2018924662","doi":"https://doi.org/10.1145/1148170.1148325","mag":"2018924662"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148325","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual 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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033159667","display_name":"Sterling Stuart Stein","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sterling Stuart Stein","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL",", Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":", Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013934685","display_name":"Shlomo Argamon","orcid":"https://orcid.org/0000-0001-8699-324X"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Argamon","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL",", Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":", Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062591304","display_name":"Ophir Frieder","orcid":"https://orcid.org/0000-0001-5076-8171"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ophir Frieder","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL",", Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":", Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":null,"apc_paid":null,"fwci":0.2443,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.46559588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"1","issue":null,"first_page":"701","last_page":"702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","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/T12380","display_name":"Authorship Attribution and Profiling","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/T10181","display_name":"Natural Language Processing Techniques","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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9933000206947327,"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":0.7420980334281921},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6665400266647339},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.5953137874603271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5861902236938477},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5165318846702576},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4440288841724396},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.41788822412490845},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4152730107307434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3251042366027832},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25835123658180237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08506852388381958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7420980334281921},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6665400266647339},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.5953137874603271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861902236938477},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5165318846702576},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4440288841724396},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.41788822412490845},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4152730107307434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3251042366027832},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25835123658180237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08506852388381958},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1148170.1148325","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323106","display_name":"Agricultural Research Development Agency","ror":"https://ror.org/01shbv660"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1543320899","https://openalex.org/W1548400861","https://openalex.org/W1966382373","https://openalex.org/W2104595931","https://openalex.org/W2123504579"],"related_works":["https://openalex.org/W2548633793","https://openalex.org/W3013279174","https://openalex.org/W2941935829","https://openalex.org/W2596247554","https://openalex.org/W4301373556","https://openalex.org/W2560936962","https://openalex.org/W2788727012","https://openalex.org/W3132372214","https://openalex.org/W4224284088","https://openalex.org/W4286571989"],"abstract_inverted_index":{"Recently,":[0],"interest":[1],"is":[2],"growing":[3],"in":[4,42],"non-topical":[5],"text":[6,27],"classification":[7,28,51],"tasks":[8],"such":[9],"as":[10],"genre":[11],"classification,":[12],"sentiment":[13],"analysis,":[14],"and":[15],"authorship":[16],"profiling.":[17],"We":[18,32],"study":[19],"to":[20],"what":[21],"extent":[22],"OCR":[23],"errors":[24,41],"affect":[25,49],"stylistic":[26,50],"from":[29],"scanned":[30],"documents.":[31],"find":[33],"that":[34],"even":[35],"a":[36],"relatively":[37],"high":[38],"level":[39],"of":[40],"the":[43],"OCRed":[44],"documents":[45],"does":[46],"not":[47],"substantially":[48],"accuracy.":[52]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
