{"id":"https://openalex.org/W2767483085","doi":"https://doi.org/10.1109/stc-csit.2017.8098815","title":"Extended list of stop words: Does it work for keyphrase extraction from short texts?","display_name":"Extended list of stop words: Does it work for keyphrase extraction from short texts?","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2767483085","doi":"https://doi.org/10.1109/stc-csit.2017.8098815","mag":"2767483085"},"language":"en","primary_location":{"id":"doi:10.1109/stc-csit.2017.8098815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/stc-csit.2017.8098815","pdf_url":null,"source":{"id":"https://openalex.org/S4306498091","display_name":"2017 12th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 12th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arrow.tudublin.ie/ittscicon/35","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062386693","display_name":"Svetlana Popova","orcid":"https://orcid.org/0000-0001-5827-984X"},"institutions":[{"id":"https://openalex.org/I201646274","display_name":"Saint Peter's University","ror":"https://ror.org/00cv1e222","country_code":"US","type":"education","lineage":["https://openalex.org/I201646274"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Svetlana Popova","raw_affiliation_strings":["Sankt-Peterburgskij gosudarstvennyj universitet, Sankt-Peterburg, Sankt-Peterburg, RU"],"affiliations":[{"raw_affiliation_string":"Sankt-Peterburgskij gosudarstvennyj universitet, Sankt-Peterburg, Sankt-Peterburg, RU","institution_ids":["https://openalex.org/I201646274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023166191","display_name":"Gabriella Skitalinskaya","orcid":"https://orcid.org/0000-0001-5006-6196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriella Skitalinskaya","raw_affiliation_strings":["MIPT (State University), Moscow, Russia Institute of Technology, Tallaght, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"MIPT (State University), Moscow, Russia Institute of Technology, Tallaght, Dublin, Ireland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062386693"],"corresponding_institution_ids":["https://openalex.org/I201646274"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.13491493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T13083","display_name":"Advanced Text Analysis Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.858993411064148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7914091944694519},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7177819609642029},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6500169634819031},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5924777984619141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5725066661834717},{"id":"https://openalex.org/keywords/stop-words","display_name":"Stop words","score":0.4433292746543884},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4253499507904053},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3458790183067322},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33804214000701904},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2949042022228241}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.858993411064148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914091944694519},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7177819609642029},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6500169634819031},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5924777984619141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5725066661834717},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.4433292746543884},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4253499507904053},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3458790183067322},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33804214000701904},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2949042022228241},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":2,"locations":[{"id":"doi:10.1109/stc-csit.2017.8098815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/stc-csit.2017.8098815","pdf_url":null,"source":{"id":"https://openalex.org/S4306498091","display_name":"2017 12th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 12th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arrow.tudublin.ie:ittscicon-1034","is_oa":true,"landing_page_url":"https://arrow.tudublin.ie/ittscicon/35","pdf_url":null,"source":{"id":"https://openalex.org/S4377196307","display_name":"Arrow - TU Dublin (Technological University Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Conference Papers","raw_type":"conferencepaper"}],"best_oa_location":{"id":"pmh:oai:arrow.tudublin.ie:ittscicon-1034","is_oa":true,"landing_page_url":"https://arrow.tudublin.ie/ittscicon/35","pdf_url":null,"source":{"id":"https://openalex.org/S4377196307","display_name":"Arrow - TU Dublin (Technological University Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Conference Papers","raw_type":"conferencepaper"},"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W32253530","https://openalex.org/W1525595230","https://openalex.org/W1907578970","https://openalex.org/W2062233052","https://openalex.org/W2064418625","https://openalex.org/W2083214110","https://openalex.org/W2083673244","https://openalex.org/W2097933135","https://openalex.org/W2121181726","https://openalex.org/W2160517426","https://openalex.org/W2167329753","https://openalex.org/W2167354646","https://openalex.org/W2169602691","https://openalex.org/W2332132381","https://openalex.org/W2395643938","https://openalex.org/W4322486232","https://openalex.org/W6639689704","https://openalex.org/W6671464686","https://openalex.org/W6683645056","https://openalex.org/W6684660662","https://openalex.org/W6685063089","https://openalex.org/W7015831105"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W4307926493","https://openalex.org/W2767483085","https://openalex.org/W100013670","https://openalex.org/W4319309671","https://openalex.org/W2964302656","https://openalex.org/W3166394675"],"abstract_inverted_index":{"In":[0,120],"this":[1,121],"paper":[2,122],"we":[3,19,104,123],"study":[4],"the":[5,29,40,57,95,98,117,133,170,177,195],"problem":[6],"of":[7,33,42,44,59,72,86,97,146],"key":[8,48,99,110],"phrase":[9,49,100,111],"extraction":[10,50,101,112],"from":[11,113],"short":[12,156],"texts":[13,18,73,140,193],"written":[14],"in":[15,116,144,162,194],"Russian.":[16],"As":[17],"consider":[20],"messages":[21],"posted":[22],"on":[23,56],"Internet":[24],"car":[25],"forums":[26],"related":[27],"to":[28,81,93],"purchase":[30],"or":[31],"repair":[32],"cars.":[34],"The":[35,64,128],"main":[36],"assumption":[37],"made":[38],"is:":[39],"construction":[41],"lists":[43],"stop":[45,87,90],"words":[46,91,165],"for":[47,109,139,155],"can":[51,78],"be":[52,79,167],"effective":[53],"if":[54],"performed":[55],"basis":[58],"a":[60,69,106],"small,":[61],"expert-marked":[62],"collection.":[63],"results":[65,130,178],"show":[66,131,179],"that":[67,132,141,180],"even":[68],"small":[70],"number":[71],"marked":[74],"by":[75],"an":[76,83],"expert":[77],"enough":[80],"build":[82],"extended":[84],"list":[85],"words.":[88],"Extracted":[89],"allow":[92],"improve":[94],"quality":[96],"algorithm.":[102],"Prior,":[103],"used":[105],"similar":[107],"approach":[108,135,182],"scientific":[114],"abstracts":[115],"English":[118,188],"language.":[119,197],"work":[124],"with":[125,187,192],"Russian":[126,196],"texts.":[127],"obtained":[129],"proposed":[134,181],"works":[136,183],"not":[137,185],"only":[138,186],"are":[142],"appropriate":[143],"terms":[145],"structure":[147],"and":[148,169],"literacy,":[149],"such":[150,158],"as":[151,159],"abstracts,":[152],"but":[153,190],"also":[154,191],"texts,":[157,189],"forum":[160],"messages,":[161],"which":[163],"many":[164],"may":[166],"misspelled":[168],"text":[171],"itself":[172],"is":[173],"poorly":[174],"structured.":[175],"Moreover,":[176],"well":[184]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}
