[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126745-en":3,"doc-seo-126745-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},126745,962084928432,"Emma Wilson","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Enhancing Hate Speech Detection in Sinhala Language on Social Media using Machine Learning","Automatic and accurate hate speech detection on social media is critical to limit harmful racism and sexism related abuse. The work addresses a key barrier: severe data sparsity that reduces classification reliability. A new Sinhala-focused pipeline combines global feature selection with traditional machine learning and analyzes hate speech characteristics. Class-based variable feature selection uses both global and local scoring to identify feature values for common models such as SVM, MNB, and RF, supported by corpus-based evaluations.","Association for Information Systems  \nAIS Electronic Library (AISeL)  \n\n| ACIS 2023 Proceedings | Australasian (ACIS) |\n| --- | --- |\n| 12-2-2023\u003Cbr>Enhancing Hate Speech Detection in Sinhala Media using Machine Learning\u003Cbr>Eranga N. Fernando\u003Cbr>University of Moratuwa, Sri Lanka, [nuwani.fernando@gmail.com](nuwani.fernando@gmail.com)\u003Cbr>[Jeremiah D. Deng](Jeremiah D. Deng)\u003Cbr>University of Otago, New Zealand, [jeremiah.deng@otago.ac.nz](jeremiah.deng@otago.ac.nz)\u003Cbr>Follow this and additional works at: [https://aisel.aisnet.org/acis2023](https://aisel.aisnet.org/acis2023) | Language on Social |\n\nRecommended Citation  \nFernando, Eranga N. and Deng, Jeremiah D., \"Enhancing Hate Speech Detection in Sinhala Language on Social Media using Machine Learning\" (2023) . ACIS 2023 Proceedings. 52.  \n[https://aisel.aisnet.org/acis2023/52](https://aisel.aisnet.org/acis2023/52)  \nThis material is brought to you by the Australasian (ACIS) at AIS Electronic Library (AISeL) . It has been accepted for inclusion in ACIS 2023 Proceedings by an authorized administrator of AIS Electronic Library (AISeL) . For more information, please [contact](contact elibrary@aisnet.org)[ elibrary@aisnet.org](contact elibrary@aisnet.org).  \nEnhancing Hate Speech Detection in Sinhala Language on Social Media using Machine Learning  \nFull research paper  \nEranga Fernando  \nDepartment of Information Technology University of Moratuwa  \nSri Lanka  \nEmail: [erangan@uom.lk](erangan@uom.lk)  \nJeremiah Deng  \nSchool of Computing University of Otago Dunedin, New Zealand  \nEmail: [jeremiah.deng@otago.ac.nz](jeremiah.deng@otago.ac.nz)  \nAbstract  \nTo counter the harmful dissemination of hate speech on social media, especially abusive outbursts of racism and sexism, automatic and accurate detection is crucial. However, a significant challenge lies in the vast sparsity of available data, hindering accurate classification. This study presents a novel approach to Sinhala hate speech detection on social platforms by coupling a global feature selection process with traditional machine learning, the research scrutinizes hate speech intricacies. A class-based variable feature selection process evaluates significance via global and local scores, identifying optimal values for prevalent classifiers. Utilizing class-based and corpus-based evaluations, we pinpoint optimal feature values for classifiers like SVM, MNB, and RF. Our results reveal notable enhancements in performance, specifically the F1-Score, underscoring how feature selection and parameter tuning work in tandem to boost model efficacy. Furthermore, the study explores nuanced variations in classifier performance across training and testing datasets, emphasizing the importance of model generalization.  \nKeywords Hate Speech, High Sparsity, Feature Selection, Class-Based Assessment  \n1 Introduction  \nAs global and local interconnectivity among people rapidly grows through the internet, social networking sites have become prominent channels for communication, information sharing, and community building (Wright andYasar 2022). However, the widespread use of these platforms has also given rise to a significant challenge-the proliferation of hate speech (Laub 2019) . Hate speech on social media poses serious threats to societal harmony, individual well-being, and freedom of expression. Detecting and mitigating hate speech in real-time is crucial to creating a safer online environment.  \nAn examination within the sociological realm carried out by Allan (Allan 2017) concentrated on the dissemination of detrimental material across diverse languages via social media platforms, stressing the significance of recognizing such content. Furthermore, a sociological study conducted in 2014 (Samaratunge and Hattotuwa 2014) delved into the importance of automated hate speech detection on social media. This research underscored cases of individuals in Sri Lanka employing Facebook as a means to spread hateful expressions.  \nThe modern Sinhala a","cbCaisAMpG5ez7ph","https://ap.wps.com/l/cbCaisAMpG5ez7ph","pdf",1014643,1,15,"English","en",105,"# 1 Introduction\n## Social media and the spread of hate speech\n## Challenges of limited resources in Sinhala\n## Proposed feature selection + machine learning approach\n## High sparsity and data complexity","[{\"question\":\"What problem does the study target in social media?\",\"answer\":\"The study targets the harmful dissemination of hate speech on social media, especially abusive outbursts tied to racism and sexism.\"},{\"question\":\"Why is hate speech detection in Sinhala particularly challenging?\",\"answer\":\"Sinhala faces limited resources, including scarce labeled data and language-specific tools, which makes classification difficult.\"},{\"question\":\"How does the proposed method improve model performance?\",\"answer\":\"It couples a global feature selection process with traditional machine learning, using class-based variable feature selection and parameter tuning to boost classifier effectiveness, reflected in improved F1-Score.\"}]","Enhancing Hate Speech Detection in Sinhala Language on Social Media using Machine Learning | PDF",1785934563,38,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"enhancing-hate-speech-detection-in-sinhala-language-on-social-media-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@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/enhancing-hate-speech-detection-in-sinhala-language-on-social-media-using-machine-learning/126745/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study target in social media?","Question",{"text":75,"@type":76},"The study targets the harmful dissemination of hate speech on social media, especially abusive outbursts tied to racism and sexism.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is hate speech detection in Sinhala particularly challenging?",{"text":80,"@type":76},"Sinhala faces limited resources, including scarce labeled data and language-specific tools, which makes classification difficult.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed method improve model performance?",{"text":84,"@type":76},"It couples a global feature selection process with traditional machine learning, using class-based variable feature selection and parameter tuning to boost classifier effectiveness, reflected in improved F1-Score.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]