[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-490692-105":59,"doc-detail-490692-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","10th-workshop-on-speech-and-language-technology-in-education-slate-22-24-august-2025-nijmegen-netherlands-feature-based-analysis-of-oral-narratives","10th Workshop on Speech and Language Technology in Education (SLaTE) - 22-24 August 2025 - Nijmegen, Netherlands - Feature-based analysis of oral narratives","","Oral narrative skills are strong predictors of later literacy development. This study analyzes features of spoken narratives by four- and five-year-old children whose oral language experts identified them as needing intervention. Using simple machine-learning methods, it compares Afrikaans and isiXhosa children’s recorded stories and examines which features best indicate typical versus at-risk development. Lexical diversity and length-based measures are informative, while articulation rate is less useful. Verb and auxiliary patterns linked to goal-directed storytelling relate to reduced intervention likelihood, informing early multilingual assessment.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/10th-workshop-on-speech-and-language-technology-in-education-slate-22-24-august-2025-nijmegen-netherlands-feature-based-analysis-of-oral-narratives/490692/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/10th-workshop-on-speech-and-language-technology-in-education-slate-22-24-august-2025-nijmegen-netherlands-feature-based-analysis-of-oral-narratives/490692.png","ImageObject",300,407,{"name":92,"@type":93},"Fahsai","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-12","2026-10-01",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of the study?","Question",{"text":112,"@type":113},"To identify which measurable features of oral narratives characterize age-appropriate storytelling in preschool children and indicate risk for later literacy difficulties.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which languages and age group are analyzed?",{"text":117,"@type":113},"The study analyzes recorded stories from Afrikaans- and isiXhosa-speaking children aged four to five, selected from low-income communities in South Africa.",{"name":119,"@type":110,"acceptedAnswer":120},"Which narrative features are found to be most informative?",{"text":121,"@type":113},"Lexical diversity (unique words) and length-based features such as mean utterance length are strong indicators of typical development, while articulation rate provides little information.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},490692,1791184797,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":24,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144},549768702563,"https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083","10th Workshop on Speech and Language Technology in Education (SLaTE) 22-24 August 2025, Nijmegen, Netherlands  \nFeature-based analysis of oral narratives from Afrikaans and isiXhosa children  \nEmma Sharratt1, Annelien Smith2, Retief Louw 1, Daleen Klop2, Febe de Wet1, Herman Kamper1  \n1Electrical and Electronic Engineering, Stellenbosch University, South Africa  \n2 Speech, Language and Hearing Therapy, Stellenbosch University, South Africa  \n[emsharratt@gmail.com](emsharratt@gmail.com)  \nAbstract  \nOral narrative skills are strong predictors of later literacy development. This study examines the features of oral narratives from children who were identified by experts as requiring intervention. Using simple machine learning methods, we analyse recorded stories from four-and five-year-old Afrikaans-and isiXhosaspeaking children. Consistent with prior research, we identify lexical diversity (unique words) and length-based features (mean utterance length) as indicators of typical development, but features like articulation rate prove less informative. Despite crosslinguistic variation in part-of-speech patterns, the use of specific verbs and auxiliaries associated with goal-directed storytelling is correlated with a reduced likelihood of requiring intervention. Our analysis of two linguistically distinct languages reveals both language-specific and shared predictors of narrative proficiency, with implications for early assessment in multilingual contexts. Index Terms: oral narratives, child speech processing, automatic assessment, literacy, feature importance, model interpretability  \n1. Introduction  \nEven before children learn to read, the ability to tell and understand stories is a key developmental skill. Oral storytelling predicts later reading proficiency [1–3] and narrative assessment can therefore help identify delayed development early on [4–8] . Yet, in many parts of the world large classroom sizes make narrative assessment impossible. Observational assessments, where teachers rely on intuition, are often inaccurate [9–11] . Our goal is to identify features that characterise age-appropriate oral narratives among preschool children in low-resource language settings. These findings aim to inform the development of more effective oral narrative assessment methods to support early identification of language difficulties in pre-literate children.  \nWe focus on Afrikaans- and isiXhosa-speaking children aged four to five from low-income communities in South Africa, where large class sizes and low literacy rates are widespread [12] . We use a dataset where children told stories based on a picture sequence (Figure 1) and answered comprehension questions. Education experts then assessed whether intervention was needed. We do a text-based analysis of the narrative transcripts, using logistic regression to predict which children may need support. In contrast to our parallel work [13], our goal here is not an accurate system for automatically identifying at-risk children, but rather to characterise the types of features that are indicative of risk using an interpretable machine learning approach. Using permutation feature importance (PFI) [14] and exploratory data analysis, we perform quantitative analyses to compare the informativeness of different features. We then compare these quantitative findings to a qualitative analysis based on traditional measures of storytelling development from speech therapy.  \nFigure 1: Three images from the six-picture cat (a) and dog (b) stories used in the MAIN protocol to elicit child narratives.  \nWe consider a range of features. As in other studies [15, 16], we find that indicative features include those measuring lexical diversity (unique words), productivity (mean utterance length) and syntactic complexity (measured using a readability index) . In contrast to other studies [17, 18], we find that speech production features such as articulation rate are of little importance. We also consider gramm","cbCaifLH9Hkb8nEa","https://ap.wps.com/l/cbCaifLH9Hkb8nEa","pdf",1098156,"English","# Abstract\n# 1. Introduction\n# 2. Data","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"To identify which measurable features of oral narratives characterize age-appropriate storytelling in preschool children and indicate risk for later literacy difficulties.\"},{\"question\":\"Which languages and age group are analyzed?\",\"answer\":\"The study analyzes recorded stories from Afrikaans- and isiXhosa-speaking children aged four to five, selected from low-income communities in South Africa.\"},{\"question\":\"Which narrative features are found to be most informative?\",\"answer\":\"Lexical diversity (unique words) and length-based features such as mean utterance length are strong indicators of typical development, while articulation rate provides little information.\"}]","10th Workshop on Speech and Language Technology in Education (SLaTE) - 22-24 August 2025 - Nijmegen, Netherlands - Feature-based analysis of oral narratives | PDF",1790841413,13]