{"id":"https://openalex.org/W3162159191","doi":"https://doi.org/10.1109/kst51265.2021.9415802","title":"A Framework for Constructing Thai Sentiment Corpus using the Cosine Similarity Technique","display_name":"A Framework for Constructing Thai Sentiment Corpus using the Cosine Similarity Technique","publication_year":2021,"publication_date":"2021-01-21","ids":{"openalex":"https://openalex.org/W3162159191","doi":"https://doi.org/10.1109/kst51265.2021.9415802","mag":"3162159191"},"language":"en","primary_location":{"id":"doi:10.1109/kst51265.2021.9415802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst51265.2021.9415802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Knowledge and Smart Technology (KST)","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/A5076174377","display_name":"Nattawat Khamphakdee","orcid":"https://orcid.org/0000-0002-0063-0657"},"institutions":[{"id":"https://openalex.org/I179193067","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50","country_code":"TH","type":"education","lineage":["https://openalex.org/I179193067"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Nattawat Khamphakdee","raw_affiliation_strings":["Natural Language and Speech Processing Laboratory, Khon Kaen University, Khon Kaen, Thailand"],"affiliations":[{"raw_affiliation_string":"Natural Language and Speech Processing Laboratory, Khon Kaen University, Khon Kaen, Thailand","institution_ids":["https://openalex.org/I179193067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008878621","display_name":"Pusadee Seresangtakul","orcid":"https://orcid.org/0000-0001-7579-2485"},"institutions":[{"id":"https://openalex.org/I179193067","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50","country_code":"TH","type":"education","lineage":["https://openalex.org/I179193067"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Pusadee Seresangtakul","raw_affiliation_strings":["Natural Language and Speech Processing Laboratory, Khon Kaen University, Khon Kaen, Thailand"],"affiliations":[{"raw_affiliation_string":"Natural Language and Speech Processing Laboratory, Khon Kaen University, Khon Kaen, Thailand","institution_ids":["https://openalex.org/I179193067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076174377"],"corresponding_institution_ids":["https://openalex.org/I179193067"],"apc_list":null,"apc_paid":null,"fwci":1.0878,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8141978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"202","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","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/T10664","display_name":"Sentiment Analysis and Opinion Mining","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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9915000200271606,"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":0.8111425042152405},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.8101053237915039},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7512115240097046},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.7313275337219238},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.641262412071228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6210113167762756},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.619443416595459},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6008067727088928},{"id":"https://openalex.org/keywords/stop-words","display_name":"Stop words","score":0.5934567451477051},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.48471879959106445},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.48073482513427734},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4564828872680664},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4503747224807739},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4395969808101654},{"id":"https://openalex.org/keywords/microblogging","display_name":"Microblogging","score":0.41897711157798767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.21446704864501953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111425042152405},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.8101053237915039},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7512115240097046},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.7313275337219238},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.641262412071228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6210113167762756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.619443416595459},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6008067727088928},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.5934567451477051},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.48471879959106445},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.48073482513427734},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4564828872680664},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4503747224807739},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4395969808101654},{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.41897711157798767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.21446704864501953},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kst51265.2021.9415802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst51265.2021.9415802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Knowledge and Smart Technology (KST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4962837726","display_name":null,"funder_award_id":"3/2559","funder_id":"https://openalex.org/F4320322335","funder_display_name":"Khon Kaen University"}],"funders":[{"id":"https://openalex.org/F4320322335","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2524168323","https://openalex.org/W2552376629","https://openalex.org/W2585620645","https://openalex.org/W2587997611","https://openalex.org/W2590061102","https://openalex.org/W2752406731","https://openalex.org/W2773787896","https://openalex.org/W2782818406","https://openalex.org/W2808079449","https://openalex.org/W2888965188","https://openalex.org/W2900680397","https://openalex.org/W2900829709","https://openalex.org/W2908234644","https://openalex.org/W2944443809","https://openalex.org/W2997159780","https://openalex.org/W3000673092","https://openalex.org/W3004443263","https://openalex.org/W3006485726","https://openalex.org/W3012480764","https://openalex.org/W3019655571","https://openalex.org/W3086369502","https://openalex.org/W3101613385","https://openalex.org/W4287812807"],"related_works":["https://openalex.org/W3163388127","https://openalex.org/W2358264916","https://openalex.org/W3185916216","https://openalex.org/W3000733727","https://openalex.org/W4225939240","https://openalex.org/W3162159191","https://openalex.org/W4313188041","https://openalex.org/W3010329803","https://openalex.org/W4380187627","https://openalex.org/W193152601"],"abstract_inverted_index":{"Unstructured":[0],"data":[1,101,103,110,180,186,209],"is":[2,45,71,116,129],"growing":[3],"rapidly":[4],"due":[5],"to":[6,16,35,54,72,78,141],"the":[7,59,89,169,196,208,215,218,223],"increase":[8],"in":[9,21,29,76,139],"various":[10],"social":[11],"media":[12],"that":[13,115,120,195,207],"allow":[14],"individuals":[15],"express":[17],"and":[18,37,41,58,84,105,125,150,168,184],"write":[19],"reviews":[20,162,183],"either":[22],"a":[23,46,62,74,80,113,117,136,164],"formal":[24],"or":[25],"informal":[26],"style.":[27],"Thus,":[28],"sentiment":[30,63,82,85,106,119,155],"analysis,":[31],"it":[32],"becomes":[33],"difficult":[34],"identify":[36],"analyze":[38],"both":[39],"positive":[40,124],"negative":[42],"reviews.":[43,190,225],"Thai":[44,81],"low-resource":[47],"language":[48],"with":[49,52,163],"few":[50],"resources":[51],"which":[53,77,140],"conduct":[55,151],"NLP":[56],"research":[57],"lack":[60],"of":[61,68,97,166,188,202,217,222],"corpus.":[64],"The":[65,93,191],"main":[66,99],"objective":[67],"this":[69],"paper":[70],"present":[73],"framework":[75,95,176,198],"construct":[79],"corpus":[83],"polarity":[86,122],"classification":[87],"utilizing":[88],"cosine":[90,170],"similarity":[91,107,156,171,220],"technique.":[92,172],"proposed":[94,197],"consists":[96],"three":[98],"steps:":[100],"collection;":[102],"preprocessing;":[104],"measurement.":[108],"Initially,":[109],"collection":[111],"generates":[112],"sub-step":[114],"manual":[118],"classifies":[121],"into":[123],"negative.":[126],"Data":[127],"preprocessing":[128,210],"then":[130],"applied.":[131],"Moreover,":[132],"we":[133],"also":[134],"created":[135],"special":[137],"database":[138],"store":[142],"text":[143],"tokenization,":[144],"convert":[145],"abbreviations,":[146],"check":[147],"spelling":[148],"errors,":[149],"stop-word":[152],"removal.":[153],"Lastly,":[154],"measurement":[157],"was":[158],"conducted":[159],"between":[160],"two":[161,224],"combination":[165],"TF-IDF":[167],"We":[173,204],"evaluated":[174],"our":[175],"by":[177],"employing":[178],"training":[179],"incorporating":[181],"3,129":[182],"testing":[185],"comprised":[187],"1,000":[189],"experiment":[192],"results":[193],"demonstrated":[194],"achieved":[199],"an":[200],"accuracy":[201,216],"81.2%.":[203],"further":[205],"observed":[206],"step":[211],"herein":[212],"significantly":[213],"affected":[214],"sentence":[219],"measurements":[221]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}