Hasil untuk "Languages and literature of Eastern Asia, Africa, Oceania"

Masike Malatji

The artificial intelligence (AI) digital divide in sub-Saharan Africa (SSA) presents significant disparities in AI access, adoption, and development due to varying levels of infrastructure, education, and policy support. This study investigates the extent of AI readiness among the top SSA countries using the 2024 Government AI Readiness Index, alongside an analysis of AI initiatives to foster inclusivity. A comparative analysis of AI readiness scores highlights disparities across nations, with Mauritius (53.94) and South Africa (52.91) leading, while Zambia (42.58) and Uganda (43.32) lag. Quartile analysis reveals a concentration of AI preparedness among a few nations, suggesting uneven AI development. The study further examines the relationship between AI readiness and economic indicators, identifying instances where AI progress does not strictly correlate with Gross Domestic Product per capita, as seen in Rwanda and Uganda. Using case studies of AI initiatives across SSA, this research contextualises quantitative findings, identifying key strategies contributing to AI inclusivity, including talent development programs, research networks, and policy interventions. The study concludes with recommendations to bridge the AI digital divide, emphasising investments in AI education, localised AI solutions, and cross-country collaborations to accelerate AI adoption in SSA.

Louise Viljoen

This article consists of an intersectional reading of Lynthia Julius’s second volume of poetry Kinderlê, published in 2024. I begin by interpreting the introductory poem in the volume, “1 Gepubliseerdiërs 13”, in which the speaker protests being consistently referred to as a “bruin digter” (a ‘brown’ or ‘coloured’ poet). I read this protest as an invitation to approach the volume through an intersectional (or matrix) rather than an essentialising (or single-axis) lens. The article then identifies aspects of intersectionality theory that will help produce a nuanced reading of Julius’s second volume, namely an understanding of the theory’s origins and the contexts in which it developed, its attention to the tension between dominant and imaginary frameworks, and its use by some researchers as a heuristic instrument and provisional concept. These theoretical vantage points guide a reading that shows how the volume explores the intersections between categories such as race, gender and class, while also adding further layers —including issues of authorship, language, religion and mental health. Special attention is given to Julius’s rewriting of Paul Celan’s famous poem “Todesfuge” in her poem “Bruinfuga” and the cycle of poems titled “Kinderlê”, which creatively re-imagines the historical killing of 32 Nama children by ‘Bushmen’ (the word that the text uses). I conclude that intersectionality can indeed function as a heuristic instrument and prism that illuminates both the complex interwoven identity categories within individual poems and the volume as a whole. 

Sukairaj Hafiz Imam, Tadesse Destaw Belay, Kedir Yassin Husse et al.

ASR has achieved remarkable global progress, yet African low-resource languages remain rigorously underrepresented, producing barriers to digital inclusion across the continent with more than +2000 languages. This systematic literature review (SLR) explores research on ASR for African languages with a focus on datasets, models and training methods, evaluation techniques, challenges, and recommends future directions. We employ the PRISMA 2020 procedures and search DBLP, ACM Digital Library, Google Scholar, Semantic Scholar, and arXiv for studies published between January 2020 and July 2025. We include studies related to ASR datasets, models or metrics for African languages, while excluding non-African, duplicates, and low-quality studies (score <3/5). We screen 71 out of 2,062 records and we record a total of 74 datasets across 111 languages, encompassing approximately 11,206 hours of speech. Fewer than 15% of research provided reproducible materials, and dataset licensing is not clear. Self-supervised and transfer learning techniques are promising, but are hindered by limited pre-training data, inadequate coverage of dialects, and the availability of resources. Most of the researchers use Word Error Rate (WER), with very minimal use of linguistically informed scores such as Character Error Rate (CER) or Diacritic Error Rate (DER), and thus with limited application in tonal and morphologically rich languages. The existing evidence on ASR systems is inconsistent, hindered by issues like dataset availability, poor annotations, licensing uncertainties, and limited benchmarking. Nevertheless, the rise of community-driven initiatives and methodological advancements indicates a pathway for improvement. Sustainable development for this area will also include stakeholder partnership, creation of ethically well-balanced datasets, use of lightweight modelling techniques, and active benchmarking.

Jessica Pidoux, Sofia Kypraiou, Sonia Kgomo et al.

Content moderation and data labelling work has shifted to the Global South, particularly Africa, where workers operate under precarious conditions while remaining invisible to users. This study addresses the gap in understanding the scope of this industry and the working conditions of African content moderation workforce through a participatory approach. We collaborated with a union of content moderators to conduct desk research, deploy a questionnaire (n=81), and gather ethnographic observations across nine months that could answer their social needs. Our findings show that content moderation operations span 43 out of 55 African countries, involving 17 major firms serving predominantly North-American and European clients, with workers facing insecurity and inadequate psychological support. We contribute the first comprehensive map of Africa's content moderation industry, demonstrate a participatory methodology that centers workers' collective actions in documenting their conditions, and apply Honneth's ``struggle for recognition'' framework to understand data workers' demands for professional acknowledgement.

Alejandro Godinez

We present HySemRAG, a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG) to automate large-scale literature synthesis and identify methodological research gaps. The system addresses limitations in existing RAG architectures through a multi-layered approach: hybrid retrieval combining semantic search, keyword filtering, and knowledge graph traversal; an agentic self-correction framework with iterative quality assurance; and post-hoc citation verification ensuring complete traceability. Our implementation processes scholarly literature through eight integrated stages: multi-source metadata acquisition, asynchronous PDF retrieval, custom document layout analysis using modified Docling architecture, bibliographic management, LLM-based field extraction, topic modeling, semantic unification, and knowledge graph construction. The system creates dual data products - a Neo4j knowledge graph enabling complex relationship queries and Qdrant vector collections supporting semantic search - serving as foundational infrastructure for verifiable information synthesis. Evaluation across 643 observations from 60 testing sessions demonstrates structured field extraction achieving 35.1% higher semantic similarity scores (0.655 $\pm$ 0.178) compared to PDF chunking approaches (0.485 $\pm$ 0.204, p < 0.000001). The agentic quality assurance mechanism achieves 68.3% single-pass success rates with 99.0% citation accuracy in validated responses. Applied to geospatial epidemiology literature on ozone exposure and cardiovascular disease, the system identifies methodological trends and research gaps, demonstrating broad applicability across scientific domains for accelerating evidence synthesis and discovery.

Mbali Nkosi, Mike Nkongolo

This study examines how public perception influences the implementation and adoption of cybersecurity frameworks in South Africa. Using the PRISMA methodology, a systematic literature review was conducted across reputable scholarly databases, yielding 34 relevant sources aligned with predefined inclusion criteria. Cybersecurity, governance, trust, privacy, cybercrime, and public opinion emerged as dominant thematic clusters. Bibliometric and thematic analyses, supported by network visualisations, revealed that while trust and public sentiment affect cybersecurity policy adoption globally, these factors have minimal influence within the South African policy landscape, despite the country's high cybercrime prevalence. In response, the study proposes a trust-centric policymaking framework designed to integrate public perception as a proactive dimension of cybersecurity governance. This framework seeks to prevent trust deficits from obstructing policy effectiveness and provides guidance for restoring trust where it has eroded.

Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty et al.

Large language models (LLMs) are now used worldwide, yet their multimodal understanding and reasoning often degrade outside Western, high-resource settings. We propose MMA-ASIA, a comprehensive framework to evaluate LLMs' cultural awareness with a focus on Asian contexts. MMA-ASIA centers on a human-curated, multilingual, and multimodally aligned multiple-choice benchmark covering 8 Asian countries and 10 languages, comprising 27,000 questions; over 79 percent require multi-step reasoning grounded in cultural context, moving beyond simple memorization. To our knowledge, this is the first dataset aligned at the input level across three modalities: text, image (visual question answering), and speech. This enables direct tests of cross-modal transfer. Building on this benchmark, we propose a five-dimensional evaluation protocol that measures: (i) cultural-awareness disparities across countries, (ii) cross-lingual consistency, (iii) cross-modal consistency, (iv) cultural knowledge generalization, and (v) grounding validity. To ensure rigorous assessment, a Cultural Awareness Grounding Validation Module detects "shortcut learning" by checking whether the requisite cultural knowledge supports correct answers. Finally, through comparative model analysis, attention tracing, and an innovative Vision-ablated Prefix Replay (VPR) method, we probe why models diverge across languages and modalities, offering actionable insights for building culturally reliable multimodal LLMs.

Boqi Chen, Ou Wei, Bingzhou Zheng et al.

Graph model generation from natural language description is an important task with many applications in software engineering. With the rise of large language models (LLMs), there is a growing interest in using LLMs for graph model generation. Nevertheless, LLM-based graph model generation typically produces partially correct models that suffer from three main issues: (1) syntax violations: the generated model may not adhere to the syntax defined by its metamodel, (2) constraint inconsistencies: the structure of the model might not conform to some domain-specific constraints, and (3) inaccuracy: due to the inherent uncertainty in LLMs, the models can include inaccurate, hallucinated elements. While the first issue is often addressed through techniques such as constraint decoding or filtering, the latter two remain largely unaddressed. Motivated by recent self-consistency approaches in LLMs, we propose a novel abstraction-concretization framework that enhances the consistency and quality of generated graph models by considering multiple outputs from an LLM. Our approach first constructs a probabilistic partial model that aggregates all candidate outputs and then refines this partial model into the most appropriate concrete model that satisfies all constraints. We evaluate our framework on several popular open-source and closed-source LLMs using diverse datasets for model generation tasks. The results demonstrate that our approach significantly improves both the consistency and quality of the generated graph models.

Mahsa Jahangiri, Afrooz Jouzdani, Hamid Reza Khalesifard

Dust layers have already been reported to have negative impacts on the radiation budget of the atmosphere. But the questions are: How does the atmospheric surface temperature change during a dust outbreak, and what is its temporal correlation with variations of the dust outbreak strength? We investigated these at selected AERONET sites, including Bahrain, IASBS, Karachi, KAUST Campus, Kuwait University, Lahore, Mezaira, Solar Village, in Southwest Asia, and Dushanbe in Central Asia, using available data from 1998 to 2024. The aerosol optical depth at 870 nm and the temperature recorded at each site are taken as measures of dust outbreak strength and atmospheric surface temperature, respectively. The Hybrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT) model and the aerosol optical depths recorded by the Moderate Resolution Imaging Spectroradiometers (MODIS) on board the Aqua and Terra satellites are used to specify the sources of the dust outbreaks. Our investigations show that in most cases, the temperature decreases during a dust outbreak, but in a considerable number of cases, the temperature rises. Temperature changes are mostly less than 5 °C. We found that a dust outbreak may affect the temperature even up to two days after its highest intensity time. This effect is more profound at sites far from large dust sources, such as IASBS in northwest Iran. For sites that are located on either a dust source or very close to it, the temperature and dust optical depth vary almost synchronously.

Antoine Caubrière, Elodie Gauthier

We present the first self-supervised multilingual speech model trained exclusively on African speech. The model learned from nearly 60 000 hours of unlabeled speech segments in 21 languages and dialects spoken in sub-Saharan Africa. On the SSA subset of the FLEURS-102 dataset, our approach based on a HuBERT$_{base}$ (0.09B) architecture shows competitive results, for ASR downstream task, compared to the w2v-bert-51 (0.6B) pre-trained model proposed in the FLEURS benchmark, while being more efficient by using 7x less data and 6x less parameters. Furthermore, in the context of a LID downstream task, our approach outperforms FLEURS baselines accuracy by over 22\%.

Mohammad Kakooei, James Bailie, Markus B. Pettersson et al.

Accurate and consistent mapping of urban and rural areas is crucial for sustainable development, spatial planning, and policy design. It is particularly important in simulating the complex interactions between human activities and natural resources. Existing global urban-rural datasets such as such as GHSL-SMOD, GHS Degree of Urbanisation, and GRUMP are often spatially coarse, methodologically inconsistent, and poorly adapted to heterogeneous regions such as Africa, which limits their usefulness for policy and research. Their coarse grids and rule-based classification methods obscure small or informal settlements, and produce inconsistencies between countries. In this study, we develop a DeepLabV3-based deep learning framework that integrates multi-source data, including Landsat-8 imagery, VIIRS nighttime lights, ESRI Land Use Land Cover (LULC), and GHS-SMOD, to produce a 10m resolution urban-rural map across the African continent from 2016 to 2022. The use of Landsat data also highlights the potential to extend this mapping approach historically, reaching back to the 1990s. The model employs semantic segmentation to capture fine-scale settlement morphology, and its outputs are validated using the Demographic and Health Surveys (DHS) dataset, which provides independent, survey-based urban-rural labels. The model achieves an overall accuracy of 65% and a Kappa coefficient of 0.47 at the continental scale, outperforming existing global products such as SMOD. The resulting High-Resolution Urban-Rural (HUR) dataset provides an open and reproducible framework for mapping human settlements, enabling more context-aware analyses of Africa's rapidly evolving settlement systems. We release a continent-wide urban-rural dataset covering the period from 2016 to 2022, offering a new source for high-resolution settlement mapping in Africa.

Sofie Dalum Kjærgaard, Sarmila Chaudhary

This article explores the amplification of challenges to sexual and reproductive healthcare provision during Nepal’s COVID-19 pandemic response and lockdown in 2020. In Nepal, the provision of essential primary healthcare is compromised by systemic weaknesses, infrastructure, and the economy. This includes healthcare and services supporting women’s sexual and reproductive health and rights (SRHR). During the pandemic, the government instituted a lockdown to control the spread of COVID-19. The government’s focus on controlling the disease, or on ‘pandemic preparedness’, amplified the pre-existing vulnerabilities in the healthcare system. Policy triage caused SRHR to be under-prioritized, widened the pre-existing gaps in the healthcare infrastructure, and compelled healthcare providers to rely more on improvisation. The article concludes by calling for a re-imagination of ‘pandemic preparedness’ as ‘lockdown preparedness’. In Nepal and in other low- and middle-income countries, ‘lockdown preparedness’ should inform pandemic responses and secure the prioritization of essential primary healthcare. Furthermore, ‘lockdown preparedness’ should direct political attention and priority towards decreasing systemic weaknesses and social inequalities, to counteract their amplification during future lockdowns.

Matthew Hines, Gregory Glatzer, Shreya Ghosh et al.

The interaction between elephants and their environment has profound implications for both ecology and conservation strategies. This study presents an analytical approach to decipher the intricate patterns of elephant movement in Sub-Saharan Africa, concentrating on key ecological drivers such as seasonal variations and rainfall patterns. Despite the complexities surrounding these influential factors, our analysis provides a holistic view of elephant migratory behavior in the context of the dynamic African landscape. Our comprehensive approach enables us to predict the potential impact of these ecological determinants on elephant migration, a critical step in establishing informed conservation strategies. This projection is particularly crucial given the impacts of global climate change on seasonal and rainfall patterns, which could substantially influence elephant movements in the future. The findings of our work aim to not only advance the understanding of movement ecology but also foster a sustainable coexistence of humans and elephants in Sub-Saharan Africa. By predicting potential elephant routes, our work can inform strategies to minimize human-elephant conflict, effectively manage land use, and enhance anti-poaching efforts. This research underscores the importance of integrating movement ecology and climatic variables for effective wildlife management and conservation planning.

Lionel Posthumus

This article offers a systematic and comprehensive account of vowel changes that take place in the inadmissible phonological sequence /VV/ within a word in Zulu. Instead of discussing vowel changes in terms of vowel coalescence, vowel elision and glide insertion (as is conventionally done) this approach discusses the vowel changes with regard to the position of the two juxtaposed vowel phonemes on the vowel chart. The resultant form is predictable in terms of five basic combinatory possibilities, namely that the first vowel is a higher vowel than the second; the first vowel is a lower vowel than the second; the first vowel is a front vowel while the second is a back vowel; the first vowel is a back vowel while the second is a front vowel or the two vowels in the inadmissible sequence /VV/ are identical vowels. This article furthermore demonstrates that palatalisation is triggered by a semi-vowel generated by the inadmissible phonological structure /VV/ in the case of diminutives and locatives derived from nouns containing a bilabial or alveolar consonant in the final syllable.

Kabir Mansingh Heimsath

David Ubilava, Justin V. Hastings, Kadir Atalay

When the prices of cereal grains rise, social unrest and conflict become likely. In rural areas, the predation motives of perpetrators can explain the positive relationship between prices and conflict. Predation happens at places and in periods where and when spoils to be appropriated are available. In predominantly agrarian societies, such opportune times align with the harvest season. Does the seasonality of agricultural income lead to the seasonality of conflict? We address this question by analyzing over 55 thousand incidents involving violence against civilians staged by paramilitary groups across Africa during the 1997-2020 period. We investigate the crop year pattern of violence in response to agricultural income shocks via changes in international cereal prices. We find that a year-on-year one standard deviation annual growth of the price of the major cereal grain results in a harvest-time spike in violence by militias in a one-degree cell where this cereal grain is grown. This translates to a nearly ten percent increase in violence during the early postharvest season. We observe no such change in violence by state forces or rebel groups--the other two notable actors. By further investigating the mechanisms, we show that the violence by militias is amplified after plausibly rich harvest seasons when the value of spoils to be appropriated is higher. By focusing on harvest-related seasonality of conflict, as well as actors more likely to be involved in violence against civilians, we contribute to the growing literature on the economic causes of conflict in predominantly agrarian societies.

Salvaggio, Federico

The present contribution discusses the role of polysemy within Ibn ʿArabī’s hermeneutic approach in the Fuṣūṣ al-Ḥikam. It argues that the Andalusian master’s conception of polysemy bears implications that stretch far beyond the field of Arabic linguistics, strictly understood, and that are tightly related to his vision of the polysemous and pansemiotic nature of existence. Thus, when investigated in the light of his metaphysical views, Ibn ʿArabī’s hermeneutic use of word polysemy, as arbitrary as it might appear at first sight, results perfectly consistent with his conception of the descent of language through multiple states of being and of the conjunction of form and meaning in the world of imagination. These metaphysical premises provide the epistemological foundations for Ibn ʿArabī’s linguistic and hermeneutic practices and build up one the finest and most complete metaphysical conceptions of language elaborated within the broader context of what might be defined the domain of ‘Islamic linguistics’.

Solomon Awuzie

As part of the third generation of Nigerian poetry, Isidore Diala’s The Lure of Ash focuses on the Nigerian Civil War experience of 1967–1970, the grief associated with it, and the resurrection of the Biafran agitation. Being a collection that is derived from the rural world of the Igbo cosmology, Diala’s The Lure of Ash portrays the Nigerian Civil War in a sensuous and emotive tone. It accounts for the poet’s belief in the regeneration of the lives of the dead Biafran soldiers. The symbols of fire and ash are significant for interpreting the poet-speaker’s grief in the collection. The collection also succeeds in painting a picture of the Nigerian Civil War experience where the bitter memory of the war resonates, while representing poetry as the healer of the pain and wounds of the war.

Sebastian Duerr, Peter A. Gloor

This literature review focuses on the use of Natural Language Generation (NLG) to automatically detect and generate persuasive texts. Extending previous research on automatic identification of persuasion in text, we concentrate on generative aspects through conceptualizing determinants of persuasion in five business-focused categories: benevolence, linguistic appropriacy, logical argumentation, trustworthiness, tools and datasets. These allow NLG to increase an existing message's persuasiveness. Previous research illustrates key aspects in each of the above mentioned five categories. A research agenda to further study persuasive NLG is developed. The review includes analysis of seventy-seven articles, outlining the existing body of knowledge and showing the steady progress in this research field.

Adyasha Maharana, Morine Amutorine, Moinina David Sengeh et al.

The use of technology has been ubiquitous in efforts to combat the ongoing public health crisis due to emergence and spread of the SARS-CoV-2 virus. African countries have made tremendous use of technology to disseminate information, counter the spread of COVID-19, and develop cutting-edge techniques to help with diagnosis, treatment and management of patients. The nature and outcomes of these efforts sometimes differ in Africa compared to other areas of the world due to its unique challenges and opportunities. Several countries have developed innovative technology-driven solutions to cater to a diverse population with varying access to technology. Much of the efforts are also earmarked by a flexible approach to problem solving, local tech entrepreneurship, and swift adoption of cutting-edge technology.