{"id":"https://openalex.org/W2162500529","doi":"https://doi.org/10.11591/ijece.v5i3.pp409-420","title":"Text Preprocessing using Annotated Suffix Tree with Matching Keyphrase","display_name":"Text Preprocessing using Annotated Suffix Tree with Matching Keyphrase","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W2162500529","doi":"https://doi.org/10.11591/ijece.v5i3.pp409-420","mag":"2162500529"},"language":"en","primary_location":{"id":"doi:10.11591/ijece.v5i3.pp409-420","doi":"https://doi.org/10.11591/ijece.v5i3.pp409-420","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijece.v5i3.pp409-420","pdf_url":"http://ijece.iaescore.com/index.php/IJECE/article/download/5634/4653","source":{"id":"https://openalex.org/S2764532672","display_name":"International Journal of Electrical and Computer Engineering (IJECE)","issn_l":"2088-8708","issn":["2088-8708"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Electrical and Computer Engineering (IJECE)","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://ijece.iaescore.com/index.php/IJECE/article/download/5634/4653","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025379579","display_name":"Ionia Veritawati","orcid":"https://orcid.org/0000-0002-4477-5786","observed_orcids":["https://orcid.org/0000-0002-4477-5786"]},"institutions":[{"id":"https://openalex.org/I3129280579","display_name":"Pancasila University","ror":"https://ror.org/0062tve42","country_code":"ID","type":"education","lineage":["https://openalex.org/I3129280579"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ionia Veritawati","raw_affiliation_strings":["Pancasila University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pancasila University","institution_ids":["https://openalex.org/I3129280579"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088280960","display_name":"Ito Wasito","orcid":"https://orcid.org/0000-0002-1107-2769","observed_orcids":["https://orcid.org/0000-0002-1107-2769"]},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ito Wasito","raw_affiliation_strings":["University of Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047887538","display_name":"Tjan Basaruddin","orcid":"https://orcid.org/0000-0002-0794-5299","observed_orcids":["https://orcid.org/0000-0002-0794-5299"]},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"T Basaruddin","raw_affiliation_strings":["University of Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Indonesia","institution_ids":["https://openalex.org/I29617571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.981,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81660753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"5","issue":"3","first_page":"409","last_page":"409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/keyword-extraction","display_name":"keyword extraction","score":0.9769999980926514},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.9929999709129333},{"id":"https://openalex.org/keywords/stop-word-removal","display_name":"stop word removal","score":0.7739999890327454},{"id":"https://openalex.org/keywords/stemming","display_name":"stemming","score":0.9980000257492065},{"id":"https://openalex.org/keywords/document-collections","display_name":"document collections","score":0.49900001287460327},{"id":"https://openalex.org/keywords/implicit-content","display_name":"implicit content","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.89935302734375},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5935128927230835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5632860064506531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333184003829956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4735102951526642},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.4547012746334076},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4430442750453949},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4407894015312195},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.41367098689079285},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16545099020004272},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.11591/ijece.v5i3.pp409-420","doi":"https://doi.org/10.11591/ijece.v5i3.pp409-420","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijece.v5i3.pp409-420","pdf_url":"http://ijece.iaescore.com/index.php/IJECE/article/download/5634/4653","source":{"id":"https://openalex.org/S2764532672","display_name":"International Journal of Electrical and Computer Engineering (IJECE)","issn_l":"2088-8708","issn":["2088-8708"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Electrical and Computer Engineering (IJECE)","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.11591/ijece.v5i3.pp409-420","doi":"https://doi.org/10.11591/ijece.v5i3.pp409-420","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijece.v5i3.pp409-420","pdf_url":"http://ijece.iaescore.com/index.php/IJECE/article/download/5634/4653","source":{"id":"https://openalex.org/S2764532672","display_name":"International Journal of Electrical and Computer Engineering (IJECE)","issn_l":"2088-8708","issn":["2088-8708"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Electrical and Computer Engineering (IJECE)","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2162500529.pdf","grobid_xml":"https://content.openalex.org/works/W2162500529.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1498024709","https://openalex.org/W1975584591","https://openalex.org/W1982026570","https://openalex.org/W2012778301","https://openalex.org/W2014545475","https://openalex.org/W2015303425","https://openalex.org/W2015469910","https://openalex.org/W2024394872","https://openalex.org/W2052286803","https://openalex.org/W2053964647","https://openalex.org/W2081028888","https://openalex.org/W2096278290","https://openalex.org/W2096437718","https://openalex.org/W2097385711","https://openalex.org/W2116091861","https://openalex.org/W2130027893","https://openalex.org/W2149522402","https://openalex.org/W2952567560","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W7096028247","https://openalex.org/W7056506402","https://openalex.org/W2951916315","https://openalex.org/W6966807304","https://openalex.org/W2895940773","https://openalex.org/W4409357105","https://openalex.org/W587841019","https://openalex.org/W1968025734","https://openalex.org/W2419400272","https://openalex.org/W4312896785"],"abstract_inverted_index":{"Text":[0],"document":[1],"is":[2,21,30,66,91],"an":[3,191],"important":[4],"source":[5],"of":[6,11,24,28,36,51,86,89,99,107,121,125,160,175,200,214],"information":[7,117],"and":[8,81,96,162,171,217],"knowledge.":[9],"Most":[10],"the":[12,62,70,141],"knowledge":[13],"needed":[14],"in":[15,22],"various":[16],"domains":[17],"for":[18,140],"different":[19],"purposes":[20],"form":[23],"implicit":[25],"content.":[26],"Content":[27],"text":[29,47,54,74,142,201],"represented":[31],"by":[32,131,223],"keyphrases,":[33],"which":[34,110,151,203,220],"consist":[35],"one":[37],"or":[38,137,178,208],"more":[39,168],"meaningful":[40],"words.":[41,225],"Keyphrases":[42],"can":[43,111,127,165,181,189,204],"be":[44,128,166,182,190],"extracted":[45,101,167,183],"from":[46,61,155,198,212],"through":[48],"several":[49],"steps":[50],"processing,":[52],"including":[53],"preprocessing.":[55],"Annotated":[56],"Suffix":[57],"Tree":[58],"(AST)":[59],"built":[60],"documents":[63,202],"collection":[64,199],"itself":[65],"used":[67,103],"to":[68,118,134,194],"extract":[69],"keyphrase,":[71],"after":[72],"basic":[73],"preprocessing":[75,90],"that":[76,158],"includes":[77],"removing":[78],"stop":[79,224],"words":[80,94,98,164],"stemming":[82],"are":[83,102,153,221],"applied.":[84],"Combination":[85],"four":[87],"variations":[88],"used.":[92],"Two":[93],"(bi-words)":[95],"three":[97,163],"phrases":[100,180,211],"as":[104],"a":[105],"list":[106,213],"keyphrases":[108,152,159,177,197,207,215,219],"candidate":[109,124,196,216],"help":[112],"user":[113],"who":[114],"needs":[115],"keyphrase":[116,126,136,139],"understand":[119],"content":[120],"documents.":[122],"The":[123,186],"processed":[129],"further":[130],"learning":[132],"process":[133],"determine":[135],"non":[138,206,209],"domain":[143],"with":[144],"manual":[145],"validation.":[146],"Experiments":[147],"using":[148,172],"simulation":[149],"corpus":[150,174],"determined":[154],"it":[156],"show":[157],"two":[161],"than":[169],"90%":[170],"real":[173],"economy,":[176],"meaning":[179,210],"about":[184],"70%.":[185],"proposed":[187],"method":[188],"effective":[192],"ways":[193],"find":[195],"reduce":[205],"detect":[218],"separated":[222]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}
