Detection and Analysis of Offensive Online Content in Hausa Language

Detection and Analysis of Offensive Online Content in Hausa Language | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Detection and Analysis of Offensive Online Content in Hausa Language Fatima Muhammad Adam, Abubakar Yakubu Zandam, Isa Inuwa-Dutse This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4266465/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract Hausa, a major Chadic language spoken by over 100 million people in Africa, faces a challenge in the digital age. While widely used, it is considered a low-resource language from a computational linguistic perspective. This means there are limited resources and tools to analyse Hausa text, making it difficult to detect offensive and threatening language online. Our study aimed to bridge this gap. We conducted two user studies (n = 180) to understand cyberbullying in Hausa. We then created the first-ever dataset of offensive and threatening Hausa phrases to train detection systems. We developed a system to flag such content and compared it to Google translation’s ability to detect these terms. Our findings revealed a concerning trend: offensive and threatening language is prevalent online, especially in discussions about religion and politics. Our detection system was able to detect more than 70% of offensive and threatening content, although many of these were mistranslated by Google’s translation engine. We attribute this to the subtle relationship between offensive and threatening content and idiomatic expressions in the Hausa language. This highlights the importance of considering cultural nuances and idiomatic expressions in Hausa. To create a safer online environment for Hausa speakers, we recommend involving diverse stakeholders who understand local contexts and demographics. This will allow for the development of more accurate detection systems and targeted moderation strategies. Trigger Warning: Readers may find some of the terms in this study distressing or disturbing; all examples are for illustration only. Low-Resource Language Hausa Language Offensive and Cyberbullying Online Social Media Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4266465","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":293262083,"identity":"f4142ca3-29c2-43f4-af40-669959f15bc0","order_by":0,"name":"Fatima Muhammad Adam","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Fatima","middleName":"Muhammad","lastName":"Adam","suffix":""},{"id":293262084,"identity":"f482b25f-b976-48d1-a37c-d1a04efc5be2","order_by":1,"name":"Abubakar Yakubu Zandam","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Abubakar","middleName":"Yakubu","lastName":"Zandam","suffix":""},{"id":293262085,"identity":"619e084e-826d-4c75-860f-317a57c1f689","order_by":2,"name":"Isa Inuwa-Dutse","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYBACNgbGBgjrAIioOABlMCQQo4UZSJwhQgsCgLQwthGhhY+Bue0xb5sdA9+N/MMfPs67k9h3gPnhB8a2NHwOazfmbUtmkLyRzCY5c9uzxJkH2IwlGNty8Glpk+bdxly/AaiFmXfb4cQNBxjMgIIVhLTUMxjcSGb+/HcOSAv7N2K0HAZpYZBmbABp4QHZgsdhzIxtknP/HWeQPPPYTLLn2GHjmYd5iiUSzuH2vnx7+zOJN2eqGfiOJz7+8KPmsGzf8faNHz6UJePUwsCMVSQBt4ZRMApGwSgYBUQAAJjFVII6k0XwAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Isa","middleName":"","lastName":"Inuwa-Dutse","suffix":""}],"badges":[],"createdAt":"2024-04-14 23:59:25","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4266465/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-4266465/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":55406180,"identity":"ddb55f69-2f7f-4440-825e-487659ebfb36","added_by":"auto","created_at":"2024-04-26 20:58:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1969167,"visible":true,"origin":"","legend":"","description":"","filename":"hoc24.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4266465/v2_covered_cea5190f-26b1-44f5-9dd8-cfcef35551c9.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eDetection and Analysis of Offensive Online Content in Hausa Language\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Low-Resource Language, Hausa Language, Offensive and, Cyberbullying, Online Social Media","lastPublishedDoi":"10.21203/rs.3.rs-4266465/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4266465/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHausa, a major Chadic language spoken by over 100 million people in Africa, faces a challenge in the digital age. While widely used, it is considered a low-resource language from a computational linguistic perspective. This means there are limited resources and tools to analyse Hausa text, making it difficult to detect offensive and threatening language online. Our study aimed to bridge this gap. We conducted two user studies (n = 180) to understand cyberbullying in Hausa. We then created the first-ever dataset of offensive and threatening Hausa phrases to train detection systems. We developed a system to flag such content and compared it to Google translation’s ability to detect these terms. Our findings revealed a concerning trend: offensive and threatening language is prevalent online, especially in discussions about religion and politics. Our detection system was able to detect more than 70% of offensive and threatening content, although many of these were mistranslated by Google’s translation engine. We attribute this to the subtle relationship between offensive and threatening content and idiomatic expressions in the Hausa language. This highlights the importance of considering cultural nuances and idiomatic expressions in Hausa. To create a safer online environment for Hausa speakers, we recommend involving diverse stakeholders who understand local contexts and demographics. This will allow for the development of more accurate detection systems and targeted moderation strategies.\u003c/p\u003e\n\u003cp\u003eTrigger Warning: Readers may find some of the terms in this study distressing or disturbing; all examples are for illustration only.\u003c/p\u003e","manuscriptTitle":"Detection and Analysis of Offensive Online Content in Hausa Language","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2024-04-26 20:42:24","doi":"10.21203/rs.3.rs-4266465/v2","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}},{"code":1,"date":"2024-04-19 16:43:50","doi":"10.21203/rs.3.rs-4266465/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1569771e-3a7b-4670-adea-317de0eabaa9","owner":[],"postedDate":"April 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-19T16:43:53+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-26 20:42:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-4266465","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4266465","identity":"rs-4266465","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}