{"id":"https://openalex.org/W4392982179","doi":"https://doi.org/10.1109/cvmi59935.2023.10465040","title":"Enhancing Large Document Organization Through Effective Preprocessing and Data Embedding","display_name":"Enhancing Large Document Organization Through Effective Preprocessing and Data Embedding","publication_year":2023,"publication_date":"2023-12-10","ids":{"openalex":"https://openalex.org/W4392982179","doi":"https://doi.org/10.1109/cvmi59935.2023.10465040"},"language":"en","primary_location":{"id":"doi:10.1109/cvmi59935.2023.10465040","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cvmi59935.2023.10465040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","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/A5093032634","display_name":"Aniruddha Shrikhande","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aniruddha Shrikhande","raw_affiliation_strings":["Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India"],"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111150601","display_name":"Saachi Shrikhande","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saachi Shrikhande","raw_affiliation_strings":["Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India"],"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039630917","display_name":"Siddhesh Borse","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddhesh Borse","raw_affiliation_strings":["Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India"],"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006230017","display_name":"Jyoti Madake","orcid":"https://orcid.org/0000-0002-5302-2508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jyoti Madake","raw_affiliation_strings":["Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India"],"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073628429","display_name":"Shripad Bhatlawande","orcid":"https://orcid.org/0000-0001-8405-9824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shripad Bhatlawande","raw_affiliation_strings":["Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India"],"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Technology,Department of Electronics and Telecommunication,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Electronics and Telecommunication, Vishwakarma Institute of Technology, Pune, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093032634"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26926564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8490999937057495,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8490999937057495,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.8223999738693237,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.7847999930381775,"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/computer-science","display_name":"Computer science","score":0.7760171890258789},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6549296379089355},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5659990906715393},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49178317189216614},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4656902551651001},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36895841360092163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3128581643104553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760171890258789},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6549296379089355},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5659990906715393},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49178317189216614},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4656902551651001},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36895841360092163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3128581643104553}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvmi59935.2023.10465040","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cvmi59935.2023.10465040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1989042107","https://openalex.org/W2963874170","https://openalex.org/W3003819547","https://openalex.org/W3082673869","https://openalex.org/W3189712965","https://openalex.org/W3199208040","https://openalex.org/W4213059241","https://openalex.org/W4293222908","https://openalex.org/W4319777676","https://openalex.org/W4321488729","https://openalex.org/W4360897584"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,69],"effective":[4],"document":[5],"classification":[6,98],"system":[7],"that":[8,21,63,79],"utilizes":[9],"modified":[10],"data":[11,37],"pre-processing":[12,35],"and":[13,31,36,53,59,86],"embedding":[14,38],"techniques.":[15],"Here":[16],"a":[17,49,54,84],"model":[18],"is":[19],"proposed":[20,81],"compares":[22],"various":[23],"machine":[24],"learning":[25],"techniques,":[26],"such":[27],"as":[28],"SVM,":[29],"KNN,":[30],"NB,":[32],"using":[33],"different":[34],"methods.":[39],"The":[40],"model's":[41],"accuracy":[42,70],"was":[43],"tested":[44],"on":[45],"two":[46],"datasets":[47],"-":[48,58],"multiclass":[50],"news":[51],"dataset":[52,57],"binary":[55],"IMDB":[56],"the":[60,80,97],"results":[61,77],"demonstrate":[62],"SVM":[64],"with":[65],"TF":[66],"-IDF":[67],"achieved":[68],"rate":[71],"of":[72,93],"95":[73],"per":[74],"cent.":[75],"These":[76],"indicate":[78],"approach":[82],"offers":[83],"reliable":[85],"efficient":[87],"method":[88],"for":[89],"handling":[90],"huge":[91],"quantities":[92],"documents":[94],"while":[95],"streamlining":[96],"procedure.":[99]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}
