{"id":"https://openalex.org/W3110771955","doi":"https://doi.org/10.1109/bigdata50022.2020.9378226","title":"Accelerating Text Mining Using Domain-Specific Stop Word Lists","display_name":"Accelerating Text Mining Using Domain-Specific Stop Word Lists","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3110771955","doi":"https://doi.org/10.1109/bigdata50022.2020.9378226","mag":"3110771955"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.02294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054682401","display_name":"Farah Alshanik","orcid":"https://orcid.org/0000-0001-5372-5070"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Farah Alshanik","raw_affiliation_strings":["Clemson University,School of Computing,Clemson,USA","Clemson University School of Computing Clemson USA"],"affiliations":[{"raw_affiliation_string":"Clemson University,School of Computing,Clemson,USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"Clemson University School of Computing Clemson USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004225206","display_name":"Amy Apon","orcid":"https://orcid.org/0000-0001-5617-5334"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amy Apon","raw_affiliation_strings":["Clemson University,School of Computing,Clemson,USA","Clemson University School of Computing Clemson USA"],"affiliations":[{"raw_affiliation_string":"Clemson University,School of Computing,Clemson,USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"Clemson University School of Computing Clemson USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014112","display_name":"Alexander Herzog","orcid":"https://orcid.org/0000-0001-7671-1878"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Herzog","raw_affiliation_strings":["Clemson University,School of Computing,Clemson,USA","Clemson University School of Computing Clemson USA"],"affiliations":[{"raw_affiliation_string":"Clemson University,School of Computing,Clemson,USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"Clemson University School of Computing Clemson USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057164472","display_name":"Ilya Safro","orcid":"https://orcid.org/0000-0001-6284-7408"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilya Safro","raw_affiliation_strings":["Clemson University,School of Computing,Clemson,USA","Clemson University School of Computing Clemson USA"],"affiliations":[{"raw_affiliation_string":"Clemson University,School of Computing,Clemson,USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"Clemson University School of Computing Clemson USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057510939","display_name":"Justin Sybrandt","orcid":"https://orcid.org/0000-0001-5073-0122"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Sybrandt","raw_affiliation_strings":["Clemson University,School of Computing,Clemson,USA","Clemson University"],"affiliations":[{"raw_affiliation_string":"Clemson University,School of Computing,Clemson,USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054682401"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":0.1359,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58238964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2639","last_page":"2648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9990000128746033,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperplane","display_name":"Hyperplane","score":0.7827575206756592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7072779536247253},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.667292058467865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5876186490058899},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5875174403190613},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5741879343986511},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5733838081359863},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5590692758560181},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5006651878356934},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.44233301281929016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4221256375312805},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3865974545478821},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32986968755722046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24197623133659363}],"concepts":[{"id":"https://openalex.org/C68693459","wikidata":"https://www.wikidata.org/wiki/Q657586","display_name":"Hyperplane","level":2,"score":0.7827575206756592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072779536247253},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.667292058467865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5876186490058899},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5875174403190613},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5741879343986511},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5733838081359863},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5590692758560181},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5006651878356934},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.44233301281929016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4221256375312805},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3865974545478821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32986968755722046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24197623133659363},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.02294","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.02294","pdf_url":"https://arxiv.org/pdf/2012.02294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3110771955","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2012.02294v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2012.02294","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.02294","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.02294","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.02294","pdf_url":"https://arxiv.org/pdf/2012.02294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3328667828","display_name":null,"funder_award_id":"1725573","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4671908575","display_name":null,"funder_award_id":"2027864","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7632170509","display_name":null,"funder_award_id":"1405767","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3110771955.pdf","grobid_xml":"https://content.openalex.org/works/W3110771955.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W978549","https://openalex.org/W298212978","https://openalex.org/W1791847295","https://openalex.org/W1924689489","https://openalex.org/W1930624869","https://openalex.org/W2097277954","https://openalex.org/W2101234009","https://openalex.org/W2110474840","https://openalex.org/W2113459411","https://openalex.org/W2121167884","https://openalex.org/W2130428585","https://openalex.org/W2141599568","https://openalex.org/W2155814520","https://openalex.org/W2185037718","https://openalex.org/W2355723585","https://openalex.org/W2467967664","https://openalex.org/W2501092290","https://openalex.org/W2520961805","https://openalex.org/W2595034312","https://openalex.org/W2782213427","https://openalex.org/W2793432814","https://openalex.org/W2806402810","https://openalex.org/W2950577311","https://openalex.org/W2963533707","https://openalex.org/W2963587534","https://openalex.org/W3007639801","https://openalex.org/W3154263804","https://openalex.org/W6636510571","https://openalex.org/W6638079928","https://openalex.org/W6675354045","https://openalex.org/W6676564027","https://openalex.org/W6676984168","https://openalex.org/W6677966481","https://openalex.org/W6679827462","https://openalex.org/W6680890276","https://openalex.org/W6686339204","https://openalex.org/W6747652377","https://openalex.org/W6794276298"],"related_works":["https://openalex.org/W3137868184","https://openalex.org/W2321447208","https://openalex.org/W3095042565","https://openalex.org/W3049560862","https://openalex.org/W2404155898","https://openalex.org/W2900278036","https://openalex.org/W2536756668","https://openalex.org/W3159982738","https://openalex.org/W25456287","https://openalex.org/W3100281586","https://openalex.org/W2186481080","https://openalex.org/W132901438","https://openalex.org/W3095317568","https://openalex.org/W2547803751","https://openalex.org/W1855811457","https://openalex.org/W2886837439","https://openalex.org/W2089685456","https://openalex.org/W3114010509","https://openalex.org/W2759863041","https://openalex.org/W3133673679"],"abstract_inverted_index":{"Text":[0],"preprocessing":[1],"is":[2,25,45,170,219],"an":[3],"essential":[4],"step":[5],"in":[6,30,35,77,129,188],"text":[7,31,92,143],"mining.":[8],"Removing":[9],"words":[10,57,76,110,218],"that":[11,194],"can":[12,140,198,228],"negatively":[13],"impact":[14],"the":[15,52,81,84,89,105,112,120,127,151,182,186,189,195,200,203,216],"quality":[16],"of":[17,51,83,91,108,122,126,202],"prediction":[18],"algorithms":[19],"or":[20],"are":[21,58],"not":[22],"informative":[23],"enough":[24],"a":[26,40,48,70,78,100],"crucial":[27],"storage-saving":[28],"technique":[29],"indexing":[32],"and":[33,87,132,164,176,180,185,207,226],"results":[34,227],"improved":[36],"computational":[37,212],"efficiency.":[38],"Typically,":[39],"generic":[41],"stop":[42],"word":[43,128],"list":[44],"applied":[46],"to":[47,63,214],"dataset":[49],"regardless":[50],"domain.":[53,72],"However,":[54],"many":[55],"common":[56,75],"different":[59,174],"from":[60,135],"one":[61],"domain":[62],"another":[64],"but":[65],"have":[66],"no":[67],"significance":[68],"within":[69],"particular":[71],"Eliminating":[73],"domain-specific":[74,109,217],"corpus":[79,204],"reduces":[80],"dimensionality":[82,144,183,201],"feature":[85,156],"space,":[86],"improves":[88],"performance":[90],"mining":[93],"tasks.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98],"present":[99],"novel":[101],"mathematical":[102],"approach":[103,117,139,153,197],"for":[104],"automatic":[106],"extraction":[107],"called":[111],"hyperplane-based":[113,138,152,196],"approach.":[114],"This":[115],"new":[116],"depends":[118],"on":[119,172],"notion":[121],"low":[123],"dimensional":[124],"representation":[125],"vector":[130],"space":[131],"its":[133],"distance":[134],"hyperplane.":[136],"The":[137,211],"significantly":[141,220],"reduce":[142,199],"by":[145,205],"eliminating":[146],"irrelevant":[147],"features.":[148],"We":[149],"compare":[150],"with":[154],"other":[155],"selection":[157],"methods,":[158],"namely":[159],"\u03c7":[160],"<sup":[161],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[163],"mutual":[165,209,223],"information.":[166,210],"An":[167],"experimental":[168],"study":[169],"performed":[171],"three":[173],"datasets":[175],"five":[177],"classification":[178,190],"algorithms,":[179],"measure":[181],"reduction":[184],"increase":[187],"performance.":[191],"Results":[192],"indicate":[193],"90%":[206],"outperforms":[208],"time":[213],"identify":[215],"lower":[221],"than":[222],"information.Reproducibility:":[224],"code":[225],"be":[229],"found":[230],"at":[231],"https://github.com/FarahAlshanik/Domain-Specific-Word-List.":[232]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}