{"id":"https://openalex.org/W4311415586","doi":"https://doi.org/10.1109/ict4da56482.2022.9971189","title":"The 5Js in Ethiopia: Amharic Hate Speech Data Annotation Using Toloka Crowdsourcing Platform","display_name":"The 5Js in Ethiopia: Amharic Hate Speech Data Annotation Using Toloka Crowdsourcing Platform","publication_year":2022,"publication_date":"2022-11-28","ids":{"openalex":"https://openalex.org/W4311415586","doi":"https://doi.org/10.1109/ict4da56482.2022.9971189"},"language":"en","primary_location":{"id":"doi:10.1109/ict4da56482.2022.9971189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ict4da56482.2022.9971189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","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/A5071390079","display_name":"Abinew Ali Ayele","orcid":"https://orcid.org/0000-0003-4686-5053"},"institutions":[{"id":"https://openalex.org/I57092466","display_name":"Bahir Dar University","ror":"https://ror.org/01670bg46","country_code":"ET","type":"education","lineage":["https://openalex.org/I57092466"]}],"countries":["ET"],"is_corresponding":false,"raw_author_name":"Abinew Ali Ayele","raw_affiliation_strings":["Bahir Dar Institute of Technology Bahir Dar University,Faculty of Computing,Bahir Dar,Ethiopia","Faculty of Computing, Bahir Dar Institute of Technology Bahir Dar University, Bahir Dar, Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bahir Dar Institute of Technology Bahir Dar University,Faculty of Computing,Bahir Dar,Ethiopia","institution_ids":["https://openalex.org/I57092466"]},{"raw_affiliation_string":"Faculty of Computing, Bahir Dar Institute of Technology Bahir Dar University, Bahir Dar, Ethiopia","institution_ids":["https://openalex.org/I57092466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007964234","display_name":"Skadi Dinter","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Skadi Dinter","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Dept. of Informatics,Hamburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Dept. of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040546523","display_name":"Tadesse Destaw Belay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114501","display_name":"Wollo University","ror":"https://ror.org/01ktt8y73","country_code":"ET","type":"education","lineage":["https://openalex.org/I4210114501"]}],"countries":["ET"],"is_corresponding":false,"raw_author_name":"Tadesse Destaw Belay","raw_affiliation_strings":["Wollo University,College of Informatics,Kombolcha,Ethiopia","College of Informatics, Wollo University, Kombolcha, Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wollo University,College of Informatics,Kombolcha,Ethiopia","institution_ids":["https://openalex.org/I4210114501"]},{"raw_affiliation_string":"College of Informatics, Wollo University, Kombolcha, Ethiopia","institution_ids":["https://openalex.org/I4210114501"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079615141","display_name":"Tesfa Tegegne Asfaw","orcid":"https://orcid.org/0000-0003-0392-9088"},"institutions":[{"id":"https://openalex.org/I57092466","display_name":"Bahir Dar University","ror":"https://ror.org/01670bg46","country_code":"ET","type":"education","lineage":["https://openalex.org/I57092466"]}],"countries":["ET"],"is_corresponding":false,"raw_author_name":"Tesfa Tegegne Asfaw","raw_affiliation_strings":["Bahir Dar Institute of Technology Bahir Dar University,ICT4D Research Center,Bahir Dar,Ethiopia","ICT4D Research Center, Bahir Dar Institute of Technology Bahir Dar University, Bahir Dar, Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bahir Dar Institute of Technology Bahir Dar University,ICT4D Research Center,Bahir Dar,Ethiopia","institution_ids":["https://openalex.org/I57092466"]},{"raw_affiliation_string":"ICT4D Research Center, Bahir Dar Institute of Technology Bahir Dar University, Bahir Dar, Ethiopia","institution_ids":["https://openalex.org/I57092466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039544387","display_name":"Seid Muhie Yimam","orcid":"https://orcid.org/0000-0002-8289-388X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Seid Muhie Yimam","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Dept. of Informatics,Hamburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Dept. of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Dept. of Informatics,Hamburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Dept. of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5549,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7294401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"114","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9994000196456909,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9994000196456909,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9593999981880188,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9348999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/amharic","display_name":"Amharic","score":0.9693347215652466},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.9301190376281738},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7046495676040649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6598070859909058},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4069772958755493},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3497268557548523},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34539371728897095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33583399653434753}],"concepts":[{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.9693347215652466},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.9301190376281738},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7046495676040649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6598070859909058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4069772958755493},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3497268557548523},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34539371728897095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33583399653434753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ict4da56482.2022.9971189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ict4da56482.2022.9971189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2056584528","https://openalex.org/W2126260542","https://openalex.org/W2293201672","https://openalex.org/W2403927777","https://openalex.org/W2604821579","https://openalex.org/W2800068017","https://openalex.org/W2807760453","https://openalex.org/W2940643755","https://openalex.org/W2963624952","https://openalex.org/W2971150411","https://openalex.org/W3004417295","https://openalex.org/W3111150675","https://openalex.org/W3173380736","https://openalex.org/W3208076653","https://openalex.org/W4205750677","https://openalex.org/W4287997204","https://openalex.org/W6752126435","https://openalex.org/W6761413067","https://openalex.org/W6771055536","https://openalex.org/W6787135330","https://openalex.org/W6805631135"],"related_works":["https://openalex.org/W2071761836","https://openalex.org/W2068668614","https://openalex.org/W3121919928","https://openalex.org/W584933867","https://openalex.org/W2021956231","https://openalex.org/W4386930358","https://openalex.org/W1972048371","https://openalex.org/W4287822602","https://openalex.org/W589849612","https://openalex.org/W3014460680"],"abstract_inverted_index":{"This":[0],"paper":[1,18],"presents":[2],"an":[3,127,135],"Amharic":[4,70],"hate":[5,71],"speech":[6,72],"annotation":[7,68],"using":[8,75,85,99,110],"the":[9,32,40,47,63,91,94,103,158,185],"Yandex":[10],"Toloka":[11],"crowdsourcing":[12,67],"platform.":[13],"The":[14,118,140,164],"dataset":[15],"for":[16,39,69],"this":[17],"is":[19,97,154,157],"collected":[20],"from":[21,29],"5":[22],"consecutive":[23],"years":[24],"in":[25,35,49],"Ethiopia":[26],"(5Js),":[27],"namely":[28],"2018-2022,":[30],"following":[31],"\u2018June\u2019":[33],"events":[34,45],"Ethiopia.":[36],"Every":[37],"June":[38],"last":[41],"five":[42],"years,":[43],"some":[44],"put":[46],"country":[48],"violence.":[50],"Accordingly,":[51],"we":[52,105],"annotate":[53,90],"5,267":[54],"tweets,":[55],"nearly":[56],"1k":[57],"tweets":[58,92],"every":[59],"year.":[60],"We":[61,77,179],"explore":[62],"main":[64],"challenges":[65],"of":[66,83,130,138,161,174],"data":[73],"collection":[74],"Toloka.":[76],"attain":[78],"a":[79,149,192],"Fliess":[80],"kappa":[81],"score":[82,129,137],"0.34":[84],"three":[86],"independent":[87],"annotators":[88],"that":[89,153],"and":[93,114,124,146,169,176,189],"gold":[95],"label":[96],"determined":[98],"majority":[100],"voting.":[101],"Using":[102],"datasets,":[104],"build":[106],"different":[107],"classification":[108],"models":[109,190],"classical":[111,119],"machine":[112,120],"learning":[113,116,121,142],"deep":[115,141],"approaches.":[117],"algorithms,":[122],"LR":[123],"SVM,":[125],"achieve":[126,148,171],"F1":[128,136,151,172],"0.49,":[131],"while":[132],"NB":[133],"archives":[134],"0.46.":[139],"algorithms":[143],"(LSTM,":[144],"BiLSTM,":[145],"CNN)":[147],"similar":[150],"score,":[152],"0.44,":[155],"which":[156],"lowest":[159],"performance":[160],"all":[162],"models.":[163],"contextual":[165],"embedding":[166],"models,":[167],"Am-FLAIR":[168],"Am-RoBERTa":[170],"scores":[173],"0.48":[175],"0.50":[177],"respectively.":[178],"publicly":[180],"release":[181],"<sup":[182,195],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[183,196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[184,197],"dataset,":[186],"source":[187],"code,":[188],"with":[191],"permissive":[193],"license.":[194],"https://github.com/uhh-lt/ethiopicmodels":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
