[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118307-en":3,"doc-seo-118307-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118307,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Hate Speech Identification in West Africa - Using Machine Learning Techniques","The rapid growth of social media over the past decade has driven a sharp increase in hate speech activities across West Africa, threatening social unity and potentially escalating intergroup tensions. This study develops a hate speech detection model by combining natural language processing methods with multiple machine learning classifiers. Hate speech data from West African countries, including Pidgin English, is collected from Twitter/X and preprocessed using word embedding, CountVectorizer, and TF-IDF. Logistic Regression, Naïve Bayes, XGBoost, DNN, and Bi-LSTM are trained, with Bi-LSTM using GloVe achieving the best results (92% accuracy, 83% F1).","HATE SPEECH IDENTIFICATION IN WEST AFRICA, USING MACHINE  \nLEARNING TECHNIQUES  \nA. A. Sosimi 1, O. Ipinnimo1, C. O. Folorunso 1*, B. A. Adim 1, E. Onoyom-Ita2  \n1Department of System Engineering, University of Lagos, Lagos, Nigeria 2Department of Electrical and Electronics Engineering, University of Cross River State, Idim Ita, Calabar, Nigeria  \n*Corresponding author's email address: [cfolorunso@unilag.edu.ng](cfolorunso@unilag.edu.ng)  \n\n| ARTICLE INFORMATION\u003Cbr>Submitted 19 January, 2024 Revised 25 February, 2024 Accepted 25 February, 2024\u003Cbr>Keywords:\u003Cbr>Hate speech machine learning\u003Cbr>natural language processing (NLP)\u003Cbr>social media | ABSTRACT\u003Cbr>The tremendous rise in social media usage over the past ten years has resulted in an extraordinary spike in hate speech activities in West Africa. Because of this, her unity is constantly in peril. This study combines relevant natural language processing techniques and machine learning classifiers to create a hate speech detection model using hate speech from West African countries, including Pidgin English, on Twitter, now ‘X’. The data was pre-processed using word embedding, CountVectorizer, and Term FrequencyInverse Document Frequency (Tf-Idf) to extract useful characteristics from the cleaned dataset. Five machine learning classifiers were used to train the dataset, these include Logistic Regression (LR), Naïve Bayes (NB), Extreme Gradient Boost (XGBoost), Deep Neural Network (DNN), and Bidirectional Long and Short-Term Memory (Bi-LSTM). The Bi-LSTM fitted on Global Vectors (GloVe) embedding produced the best experiment results, with an accuracy of 92% and an F1-Score of 83% when assessed on a test set. The machine learning models generally demonstrated strong performance on test data, suggesting that they had internalised the knowledge from the training set and could use it to analyse new data. |\n| --- | --- |\n\n1.0 Introduction  \nHate speech is becoming a bigger problem across the globe, especially in West Africa. The widespread use of social media and other digital platforms has made it easier for hate speech to spread quickly, escalating tensions and endangering national and local unity. Hate speech has been shown to widen differences between various ethnic, religious, and social groups and to inspire violence in West Africa as well as other regions of the world (Laub, 2019). This phenomenon can be especially unstable in nations where the population is heterogeneous and intergroup conflicts have historically occurred. In West Africa, efforts to combat hate speech frequently combine legislative actions, such as passing legislation prohibiting it, with educational programmes designed to foster tolerance, understanding, and respect for variety. Furthermore, community-based initiatives and forums for discussion can be extremely important in promoting improved social cohesiveness and lessening the negative effects of hate speech. Coordination of reactions to hate speech and the encouragement of regional collaboration in tackling this issue may also be the responsibilities of regional organisations such as the Economic Community of West African States (ECOWAS) (Daka, 2023) .  \nIn recent years, hate speech in West Africa has intensified tensions and posed a serious threat to unity in the continent (Akanji, 2017) . This has prompted the government to think about  \npassing laws that will punish anyone discovered to have used hate speech (Asogwa and Ezeibe, 2022). For instance, in Nigeria, the National Commission for the Prohibition of Hate Speech was created to assist with investigations and criminal prosecutions (Independent National Commission, 2019) . It is much simpler to keep an eye on the hate speech that appears in traditional mainstream media like television, radio, and print than it is to keep an eye on online, on sites like social media and microblogging services. This is mostly caused by the significant amount of daily content produced in internet media that needs to b","cbCaijlo7U2lvgJo","https://ap.wps.com/l/cbCaijlo7U2lvgJo","pdf",635628,1,18,"English","en",105,"# Introduction\n## Background and regional impact\n## Existing efforts and challenges","[{\"question\":\"Why is hate speech identification important in West Africa?\",\"answer\":\"Social media and digital platforms accelerate the spread of hate speech, widening divisions among ethnic, religious, and social groups and increasing risks to unity and public safety.\"},{\"question\":\"Which datasets and languages are used in the study?\",\"answer\":\"The model is trained using hate speech data from West African countries collected from Twitter/X, including Pidgin English.\"},{\"question\":\"How is the text data preprocessed before model training?\",\"answer\":\"The dataset is cleaned and then processed using word embedding, CountVectorizer, and TF-IDF to extract useful features.\"}]","Hate Speech Identification in West Africa - Using Machine Learning Techniques | PDF",1785682952,45,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"hate-speech-identification-in-west-africa-using-machine-learning-techniques","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/hate-speech-identification-in-west-africa-using-machine-learning-techniques/118307/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is hate speech identification important in West Africa?","Question",{"text":76,"@type":77},"Social media and digital platforms accelerate the spread of hate speech, widening divisions among ethnic, religious, and social groups and increasing risks to unity and public safety.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which datasets and languages are used in the study?",{"text":81,"@type":77},"The model is trained using hate speech data from West African countries collected from Twitter/X, including Pidgin English.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the text data preprocessed before model training?",{"text":85,"@type":77},"The dataset is cleaned and then processed using word embedding, CountVectorizer, and TF-IDF to extract useful features.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]