{"id":"https://openalex.org/W4380551147","doi":"https://doi.org/10.1145/3580305.3599904","title":"SentiGOLD: A Large Bangla Gold Standard Multi-Domain Sentiment Analysis Dataset and Its Evaluation","display_name":"SentiGOLD: A Large Bangla Gold Standard Multi-Domain Sentiment Analysis Dataset and Its Evaluation","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4380551147","doi":"https://doi.org/10.1145/3580305.3599904"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.06147","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101963954","display_name":"Md. Ekramul Islam","orcid":"https://orcid.org/0000-0001-8494-1809"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Md. Ekramul Islam","raw_affiliation_strings":["Giga Tech Limited, Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Giga Tech Limited, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010392592","display_name":"Labib Chowdhury","orcid":"https://orcid.org/0000-0002-5287-8267"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Labib Chowdhury","raw_affiliation_strings":["Giga Tech Limited, Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Giga Tech Limited, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070680384","display_name":"Faisal Ahamed Khan","orcid":"https://orcid.org/0000-0001-7377-1226"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faisal Ahamed Khan","raw_affiliation_strings":["Giga Tech Limited, Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Giga Tech Limited, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103071838","display_name":"Shazzad Hossain","orcid":"https://orcid.org/0000-0002-7113-1513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shazzad Hossain","raw_affiliation_strings":["Giga Tech Limited, Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Giga Tech Limited, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054937458","display_name":"Md. Sourave Hossain","orcid":"https://orcid.org/0000-0001-7436-9925"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Sourave Hossain","raw_affiliation_strings":["Giga Tech Limited, Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Giga Tech Limited, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047231876","display_name":"Mohammad Mamun Or Rashid","orcid":"https://orcid.org/0000-0001-6517-2039"},"institutions":[{"id":"https://openalex.org/I2802663610","display_name":"Bangladesh Medical Research Council","ror":"https://ror.org/03428zt70","country_code":"BD","type":"government","lineage":["https://openalex.org/I2802663610"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mohammad Mamun Or Rashid","raw_affiliation_strings":["Bangladesh Computer Council, Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Bangladesh Computer Council, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I2802663610"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062072064","display_name":"Nabeel Mohammed","orcid":"https://orcid.org/0000-0002-7661-3570"},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Nabeel Mohammed","raw_affiliation_strings":["North South University, Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"North South University, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028396045","display_name":"Mohammad Ruhul Amin","orcid":"https://orcid.org/0000-0001-6540-3415"},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Ruhul Amin","raw_affiliation_strings":["Fordham University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Fordham University, New York, NY, USA","institution_ids":["https://openalex.org/I164389053"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101963954"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6576,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91755114,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4207","last_page":"4218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/bengali","display_name":"Bengali","score":0.9344850778579712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458956241607666},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.698014497756958},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6624400019645691},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6518675088882446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6185531616210938},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5713144540786743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5542758703231812},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5202585458755493},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5150968432426453},{"id":"https://openalex.org/keywords/cohens-kappa","display_name":"Cohen's kappa","score":0.4771025776863098},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4453825354576111},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3416706919670105},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20916995406150818},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13210520148277283},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10231167078018188}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9344850778579712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458956241607666},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.698014497756958},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6624400019645691},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6518675088882446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6185531616210938},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5713144540786743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5542758703231812},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5202585458755493},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5150968432426453},{"id":"https://openalex.org/C163864269","wikidata":"https://www.wikidata.org/wiki/Q1107106","display_name":"Cohen's kappa","level":2,"score":0.4771025776863098},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4453825354576111},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3416706919670105},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20916995406150818},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13210520148277283},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10231167078018188},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3580305.3599904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.06147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.06147","pdf_url":"https://arxiv.org/pdf/2306.06147","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.06147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.06147","pdf_url":"https://arxiv.org/pdf/2306.06147","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325821","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380551147.pdf","grobid_xml":"https://content.openalex.org/works/W4380551147.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W78147652","https://openalex.org/W658020064","https://openalex.org/W1578503079","https://openalex.org/W1614298861","https://openalex.org/W1975879668","https://openalex.org/W2113459411","https://openalex.org/W2131744502","https://openalex.org/W2160660844","https://openalex.org/W2251939518","https://openalex.org/W2470673105","https://openalex.org/W2614322402","https://openalex.org/W2896457183","https://openalex.org/W2979826702","https://openalex.org/W2991128138","https://openalex.org/W3022782624","https://openalex.org/W3023225653","https://openalex.org/W3035507081","https://openalex.org/W3105168542","https://openalex.org/W3121726600","https://openalex.org/W3126191299","https://openalex.org/W3138771162","https://openalex.org/W3155743827","https://openalex.org/W3157164164","https://openalex.org/W3158629662","https://openalex.org/W3210147767","https://openalex.org/W3212697960","https://openalex.org/W4206081398","https://openalex.org/W4242959488","https://openalex.org/W4281390663","https://openalex.org/W4287484552","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W2794758919","https://openalex.org/W4232781930","https://openalex.org/W1913642778","https://openalex.org/W2630858571","https://openalex.org/W4300860228","https://openalex.org/W4212978906"],"abstract_inverted_index":{"In":[0,170],"this":[1,127],"study,":[2],"we":[3],"present":[4],"a":[5,22,29,41,59,143,186,193,230,234,253,282],"Bangla":[6,62,248],"multi-domain":[7],"sentiment":[8,69,313],"analysis":[9,70,314],"dataset,":[10,128,244],"named":[11],"as":[12,233],"SentiGOLD,":[13,295],"developed":[14],"using":[15,140,156,205],"70,000":[16],"samples,":[17,250],"which":[18,209,245,273,304],"was":[19,36,90,138,154,223,239],"compiled":[20],"from":[21,105,142,299],"variety":[23],"of":[24,32,44,56,126,145,203,285],"sources":[25],"and":[26,58,75,112,116,119,131,153,167,220,266,296],"annotated":[27],"by":[28,97,262],"gender-balanced":[30],"team":[31],"linguists.":[33],"This":[34,197],"dataset":[35],"created":[37,139],"in":[38,85,192,213,225],"accordance":[39],"with":[40],"standard":[42,68,92],"set":[43],"linguistic":[45],"conventions":[46],"that":[47],"were":[48,134],"established":[49],"after":[50],"multiple":[51],"meetings":[52],"between":[53],"the":[54,124,176,214,242,292,308],"Government":[55],"Bangladesh":[57],"nationally":[60],"recognized":[61],"linguistics":[63,93,178],"committee.":[64],"Although":[65],"there":[66,79,89],"are":[67,80],"datasets":[71,84],"available":[72],"for":[73,218,288,294,301],"English":[74],"other":[76,121],"rich":[77],"languages,":[78],"not":[81],"any":[82],"such":[83],"Bangla,":[86],"especially":[87],"because,":[88],"no":[91],"framework":[94],"agreed":[95],"upon":[96,212],"national":[98,177],"stakeholders.":[99],"Senti-GOLD":[100],"derives":[101],"its":[102],"raw":[103],"data":[104,141],"online":[106],"video":[107],"comments,":[108,113,117],"social":[109],"media":[110],"posts":[111,115],"blog":[114],"news":[118],"numerous":[120],"sources.":[122],"Throughout":[123],"development":[125],"domain":[129],"distribution":[130,133],"class":[132],"rigorously":[135],"maintained.":[136],"SentiGOLD":[137],"total":[144],"30":[146],"domains":[147],"(e.g.":[148,159],"politics,":[149],"entertainment,":[150],"sports,":[151],"etc.)":[152],"labeled":[155],"5":[157,289],"classes":[158,290,303],"strongly":[160,168],"negative,":[161,163],"weakly":[162,165],"neutral,":[164],"positive,":[166],"positive).":[169],"order":[171],"to":[172,184,228,307],"maintain":[173],"annotation":[174,182,195],"quality,":[175],"committee":[179],"approved":[180],"an":[181,200],"scheme":[183],"ensure":[185],"rigorous":[187],"Inter":[188],"Annotator":[189],"Agreement":[190],"(IAA)":[191],"multi-annotator":[194],"scenario.":[196,256],"procedure":[198],"yielded":[199],"IAA":[201],"score":[202],"0.88":[204],"Fleiss'":[206],"kappa":[207],"method,":[208],"is":[210],"elaborated":[211],"paper.":[215],"A":[216],"protocol":[217],"intra-":[219],"cross-dataset":[221,237,260],"evaluation":[222,238],"utilized":[224],"our":[226,267,275],"efforts":[227],"develop":[229],"classification":[231],"system":[232],"standard.":[235],"The":[236],"performed":[240,259],"on":[241],"SentNoB":[243],"contains":[246],"noisy":[247],"text":[249],"thereby":[251],"establishing":[252,291],"demanding":[254],"test":[255],"We":[257],"also":[258],"testing":[261],"employing":[263],"zero-shot":[264],"experiments,":[265],"best":[268],"model":[269,280],"produced":[270],"competitive":[271],"performance,":[272],"exemplify":[274],"dataset's":[276],"generalizability.":[277],"Our":[278,311],"top":[279],"attained":[281],"macro":[283],"f1":[284],"0.62":[286],"(intra-dataset)":[287],"benchmark":[293],"0.61":[297],"(cross-dataset":[298],"SentNoB)":[300],"3":[302],"stands":[305],"comparable":[306],"current":[309],"state-of-the-art.":[310],"fine-tuned":[312],"model\\footnotehttps://sentiment.bangla.gov.bd":[315],"can":[316],"be":[317],"accessed":[318],"online.":[319]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2023-06-14T00:00:00"}