Loading...

    Submit Your PaperJournalsTrack Article StatusAPC
    AB Journals logo

    An international journal platform supporting research and innovation by making knowledge accessible to everyone, everywhere.

    15442 Ventura Blvd., Ste 201-1717, Sherman Oaks, California, 91403, USA.
    +1 (213) 371-4405
    WhatsApp: +1 (313) 787-3690
    XFacebookLinkedInInstagramYoutube

    Get Journal Updates

    Stay informed about newly published articles, latest issues, and announcements from your selected journals.

    Select Journals

    Receive updates by email. Unsubscribe at any time.

    For Authors

    • Submit Your Paper
    • Track Article Status
    • Editorial Process
    • Guidelines Hub
    • Manuscript Requirements
    • Submission Guidelines
    • Article Processing Charges
    • Pay APC
    • Open Access Policy
    • Waiver Policy

    Journal Subject

    • Management Sciences
    • Humanities & Social Sciences
    • Education
    • Sciences
    • Engineering

    About

    • About AB Journal
    • Policies & Ethics
    • Contact Us
    • Feedback
    • FAQs
    • Terms
    • Privacy Policy

    Resources

    • For Reviewers
    • For Editors
    • For Authors
    • Why Publish With Us

    Copyright © 2026 AB Journals. All rights reserved.

    Open Access
    AB Journals logo
    1. Home
    2. Search Results
    Submit Your PaperJournalsTrack Article StatusAPC

    Showing 48 results found

    Keywords
    ArticleResearch Article
    An AI-Driven, Workflow-Aware Virtual Customer Support Assistant for Small and Medium-Sized Enterprises
    Damilare Akinwunmi, Sunday Oladipo, Eromoigbe Winner Agbonikpeya, Valerian Olisaemeka Ejezie, Victor Finecountry-Okezie, Dayo Francis Akinyeke, Uchenna Chidi-Aja, Evelyn-Ruth Okiemute Ijomoni, Oluwanifemi Joseph Gbambisomo, Samuel Ugonna Emeka-Ukandu, Oluwafiyinsola Praise Akenroye, Oluwatobiloba Joshua Adekunle, Oluwatobiloba David Fasakin, Esther Fisayomi Aiyenimelo
    November 16, 2026•DOI: 10.52589/AJSTE-CSGFXK•Volume 6 Issue 2•100 views
    Small and medium-sized enterprises (SMEs) that sell through messaging platforms often handle customer enquiries manually, leading to fragmented conversations, delayed responses and inconsistent service. This article proposes a workflow-aware conversational support assistant that combines a large language model (LLM), retrieval grounding, merchant API tools and context-preserving human hand-off. Using a design-science-oriented literature synthesis, in which sources were identified through keyword searches of academic databases, screened for relevance to messaging-based SME support and LLM-agent design, and analysed thematically, the study derives three design priorities: grounding customer-facing claims in current merchant data, separating model reasoning from validated execution, and transferring accumulated conversational state when escalation occurs. The resulting five-layer architecture comprises messaging integration, agent orchestration, retrieval and grounding, store action, and escalation and hand-off. Volatile data such as price, inventory and order status are retrieved live; state-changing operations require explicit customer confirmation and schema validation before execution. The article also specifies an evaluation protocol based on scripted end-to-end customer journeys using journey completion, factual agreement, action correctness, escalation precision and recall, context preservation, and response latency. The contribution is architectural and methodological; implementation and empirical validation remain future work. Read more
    Keywords:Conversational CommerceCustomer Support AutomationHuman-in-the-Loop EscalationLarge Language Models (LLMs)Retrieval-Augmented Generation (RAG)Small and Medium-Sized Enterprises (SMEs)Tool-Augmented Agents
    ArticleResearch Article
    School Infrastructure as a Determinant of Management Efficiency and English Language Academic Outcomes in UBE Schools in Gboko
    Winifred Dooshima Anikpa , Victoria Aluershima Amachigh
    November 3, 2026•DOI: 10.52589/BJELDP-HGGLBW•Volume 9 Issue 2•1,834 views
    This study investigated school infrastructure as a determinant of management efficiency and English Language academic outcomes in UBE schools in Gboko, Benue State, Nigeria. Three research questions and three null hypotheses were formulated to guide this study. The study used a survey design. The population of the study consists of 450 UBE teachers and a sample of 135 teachers was selected using a random sampling technique. The instruments for data collection were a self-structured questionnaire as well as direct assessment of availability and conditions of school infrastructure, and students’ academic outcomes in English Language (English language examination records). Mean and standard deviation were used in answering research questions 1 and 2, while Spearman’s correlation coefficient was employed in answering research question 3 and testing of hypotheses 1 and 2 at 0.05 level of significance. Hypothesis 3 was tested using independent student t-test. The findings rejected all three null hypotheses and revealed that school infrastructural facilities are critical determinants of management efficiency and students’ academic outcomes in English Language in UBE schools. The Study recommended that Government should increase funding for the provision and maintenance of school infrastructural facilities in UBE schools. School libraries should be equipped with current textbooks, and ICT facilities. Read more
    Keywords:Academic Outcomes in English LanguageManagement EfficiencySchool InfrastructureUniversal Basic Education (UBE)
    ArticleResearch Article
    Enhancing Communicative Competence in English through Play-Based Language Activities: Implications for English Language Teaching in Basic Schools
    Aikins Addae
    November 2, 2026•DOI: 10.52589/BJCE-NKNCAX•Volume 6 Issue 3•185 views
    This study examined the extent to which play-based language activities improve learners’ communicative competence in English and explored teachers’ and learners’ perceptions of their contribution to English language learning in basic schools. The study adopted an explanatory sequential mixed-methods design guided by the pragmatist paradigm. The quantitative phase employed a one-group pre-test–post-test quasi-experimental design involving 45 Basic Seven learners selected through census sampling. The qualitative phase involved semi-structured interviews with two English language teachers and 10 purposively selected learners. Data were collected through a communicative competence achievement test and interview guides. Quantitative data were analysed using descriptive statistics and paired-samples t-test, while qualitative data were analysed thematically. The findings revealed that participation in play-based language activities improved learners’ communicative competence in English. Teachers and learners perceived the activities as enhancing vocabulary development, oral communication, pronunciation, confidence, classroom participation, collaboration, and motivation to use English in authentic communicative situations. The study concludes that play-based language activities are a valuable pedagogical approach for developing communicative competence in English. It recommends that English language teachers integrate structured play-based activities into classroom instruction and that teacher education programmes strengthen teachers’ capacity to implement play-based pedagogies effectively. Read more
    Keywords:Basic SchoolsCommunicative Competence in EnglishEnglish Language TeachingLearner-Centred PedagogyMixed MethodsPlay-Based Language Activities
    ArticleResearch Article
    The Role Language of Choice in Construction and Negotiation of Social Identities among Church Members in Multilingual Churches
    Kaberere Ann Nyambura, Jane Ombati, Alexender Meitamei
    October 27, 2026•DOI: 10.52589/IJLLL-AXLJAX•Volume 9 Issue 2•142 views
    Multilingual churches are significant places that not only serve as a medium of communication but also as a tool for building and negotiating social identity. Language diversity in churches has grown and escalated the importance of investigating the role of language use on church members’ experiences of belonging, participation and inclusion in worship. This study focused on the role of language choice in the construction and negotiation of social identities of church members in the multilingual churches in Kajiado North Sub-County, Kenya. The study adopted descriptive research design where 377 church members were surveyed using questionnaire and interview. Data analysis involved descriptive statistics for quantitative data and thematic and discourse analysis for qualitative data. The results indicated that language choice had a significant effect on how social identity was formed and expressed, as it affected the sense of belonging, participation and acceptance of the members in the church communities. English, Kiswahili, indigenous Kenyan languages and code-switching were strategically used to help churches respond to the linguistic diversity of congregants, boost common religious identities and reduce social exclusion. This sometimes led to an experience of marginalization for certain members of the congregation; however, as these were seen as dominant languages, often the relationship between language, power and identity was complex in multilingual worship contexts. Read more
    Keywords:Language ChoiceSocial Identity ConstructionMultilingual ChurchesSocial Identity Negotiation
    ArticleResearch Article
    The Transformative Power of Technology in Teaching Specific Language Skills
    Dhuha S. Raheem
    October 16, 2026•DOI: 10.52589/BJCE-G3LWJEUM•Volume 6 Issue 2•243 views
    Technology advancement has paved a new way for seamless language education, redesigning instructional strategies, learning paradigms, and assessment initiatives. This research has critically analysed the transformative impact of technology in curating specific language skills through a review of existing literature study and empirical evidence through statistical evaluation. Based on this analysis, Cronbach’s Alpha value is 0.834 exploring strong internal consistency across 16 items. This value is higher than the accepted threshold value of Cronbach’s Alpha that is 0.70. It enhances the relevance of this research and ensures the credibility of the survey instruments as well. Read more
    Keywords:Artificial IntelligenceLanguage LearningDigital transformationDigital technologiesInnovationCommunicationTechnological CompetenciesStudent Engagement
    ArticleResearch Article
    Foundations and Frontiers of Swahili Natural Language Processing
    Benjamin Kikwai, Jared Ongaro
    October 12, 2026•DOI: 10.52589/AJMSS-QDF2CVCU•Volume 9 Issue 3•298 views
    Swahili serves as a lingua franca for over 200 million speakers across East and Central Africa, functioning as a critical engine for digital societal interaction and economic integration. Despite its extensive demographic prominence, it remains acutely under-resourced within the computational domain of Natural Language Processing (NLP). This article presents a mathematically rigorous, systematic review of the Swahili NLP landscape, charting its historical trajectory from acute data scarcity to an emerging ecosystem of statistically specialised tools and representations. We comprehensively catalogue and mathematically categorise primary labelled datasets deployed for classification and generative tasks, including sentiment analysis, automatic speech recognition (ASR), and abstractive summarisation. Furthermore, we analyse the parameter optimisation, tokenisation dynamics, and architectural efficacy of dedicated foundational language models—such as SwahBERT, AfriBERTa, and specialised Large Language Models (LLMs)—mapping their performance bounds against Swahili’s highly agglutinative morphology. Beyond a mere structural inventory, this review critically exposes the “resource quality gap”, identifying profound statistical deficiencies in domain-specific corpora across high-stakes fields such as healthcare and law, whilst highlighting an acute lack of dialectal variance and fine-grained annotation schemes. The analysis concludes that while generalised parameter spaces have expanded, the absence of unified benchmarking infrastructures impedes systematic algorithmic validation. Finally, we propose actionable, statistically sound methodologies for future research, advocating for the collaborative construction of comprehensive multi-task benchmarks to bridge the digital divide for the Swahili-speaking populace. Read more
    Keywords:Swahili NLPStatistical Language ModellingResource ScarcityAgglutinative MorphologyComputational Linguistics
    ArticleResearch Article
    Design and Implementation of a Sentence-BERT-Driven Semantic Matching Model for Automated Evaluation of Theory Answers
    Emmanuel Mgbeahuruike, Chris-Esezobor Ejodamen, Nelson-Nwanoneze Samuel, Obiekwe Kaima Alvin, Mesigo Chidera Sharon, Okeowo Ameenat Mofeoluwa, Esedo Adaeze Stephanie
    September 3, 2026•DOI: 10.52589/BJCNIT-419KV5SU•Volume 9 Issue 2•402 views
    Theory-based assessments remain one of the hardest grading challenges to automate. Students rarely express correct answers the way a model answer expects, and the keyword-matching tools built into most learning management systems penalise them for it, not because they are wrong, but because they phrased things differently. EvalAI addresses this by grading theory answers on meaning rather than wording, using Sentence-BERT to measure how semantically similar a student's response is to a lecturer-provided reference answer. Grading suggestions are surfaced to the lecturer, who retains full control over final marks. Evaluation against Mohler's short-answer grading benchmark yielded a Pearson correlation of 0.81 and a mean absolute error of 0.18, indicating that the system's suggestions align closely with human judgement. All functional test cases passed during system testing, and evaluators from both lecturer and student roles completed their tasks without assistance. The results show that semantic grading of this quality can be delivered within a deployable web application without specialised machine learning infrastructure, while keeping the lecturer firmly in the grading loop. Read more
    Keywords:Automated short-answer gradingSentence-BERTSemantic similarityCosine similarityEducational assessmentNatural language processing
    ArticleResearch Article
    A Retrieval-Augmented Large Language Model for Dynamic Personalization in Intelligent Tutoring Systems.
    Kuyoro Afolashade, Nzenwata Uchenna, Akinwunmi Damilare
    July 27, 2026•DOI: 10.52589/BJCNIT-2MVXUYXK•Volume 9 Issue 2•312 views
    This article presents a novel approach to Intelligent Tutoring Systems (ITS) by integrating Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) to enable dynamic personalization in educational contexts. The system addresses limitations in traditional ITS that rely on static, rule-based approaches by implementing a three-layered architecture combining semantic retrieval mechanisms with generative AI capabilities. Using GPT-4 as the core LLM enhanced with a custom RAG framework, the system demonstrates improvements in response accuracy (93%), inference speed (2.1 seconds per prompt), and computational efficiency compared to a standard GPT-4 baseline, a traditional rule-based ITS, and an LLM with keyword-based retrieval. The research employs both ASSISTments (fine-grained interaction data) and EdNet (large-scale longitudinal data) datasets for evaluation. Results show that the RAG-enhanced system achieves 40% better contextual relevance compared to standard LLM implementations. The framework incorporates adaptive prompting strategies, real-time knowledge base updates, and multi-level personalization algorithms to create a dynamic educational environment. Read more
    Keywords:Retrieval-Augmented Generation (RAG)Large Language Models (LLMs)Intelligent Tutoring Systems (ITS)Dynamic PersonalizationAdaptive LearningArtificial IntelligenceGenerative AI.
    ArticleResearch Article
    Design and Implementation of an AI-Powered Task Management System (TaskWise).
    Olawunmi Asake Adebanjo, Adebowale Oluwasegun, Anuriam Isaac, Adewuyi Joseph Oluwaseyi, Agoha Emmanuel
    June 18, 2026•DOI: 10.52589/BJCNIT-LA6S3NNL•Volume 9 Issue 2•490 views
    Managing tasks across academic, personal, and professional life remains a persistent struggle for most people, even with the growing number of digital tools available. The problem is not a shortage of apps—it is that the vast majority of them still require users to do most of the work manually: typing out tasks, setting deadlines one at a time, and remembering to check back. There is little to no intelligence built into these platforms to anticipate what a user might need next. This paper introduces TaskWise, a task management application that takes a different approach. Rather than forcing users into rigid input forms, TaskWise lets them type or speak commands in plain English—for example, “Remind me to submit my assignment by Friday”—and the system interprets those instructions to create, schedule, and organise tasks on their behalf. The application was built on a three-tier architecture: React and Tailwind CSS handle the frontend interface, Firebase Cloud Functions drive the backend logic, and Firestore provides real-time data synchronisation across devices. We also incorporated an AI-powered conversational assistant that can generate study plans, suggest tasks based on context, and respond to user queries in a natural, conversational tone. Testing with a small group of university students showed that users could create tasks significantly faster with the natural-language input compared to traditional form-based entry, and the System Usability Scale score came in at 82 out of 100. While the current version is still a prototype with clear limitations—particularly around offline support and team collaboration—TaskWise demonstrates that combining AI with cloud infrastructure can meaningfully reduce the friction involved in day-to-day task management. Read more
    Keywords:Natural Language Processing; Task Automation; Firebase; Cloud Synchronization; AI Assistant; Productivity Systems.
    ArticleResearch Article
    MedLing: A Multilingual Natural Language Processing Framework for Medical Diagnosis Support System.
    Adegbola Adesoji, Umaru Victor, Odebunmi Adeoluwasubomi, Olaitan Temitayo
    June 18, 2026•DOI: 10.52589/BJCNIT-CCFBCWM7•Volume 9 Issue 2•499 views
    Access to digital healthcare in Nigeria remains limited by language barriers, as most medical platforms are designed primarily in English, while a large portion of the population communicates in indigenous languages. This gap often prevents users from accurately describing symptoms, restricting effective communication and access to appropriate healthcare services. This study presents a multilingual medical diagnosis system capable of accepting symptom descriptions in English, Yoruba, Igbo, Hausa, and Nigerian Pidgin. The system generates ranked differential diagnoses with clinically grounded descriptions and treatment recommendations delivered in the user’s preferred language. Using advances in Natural Language Processing, the framework employs the Aya Expanse 8B model, deployed through Ollama, to translate indigenous inputs into English for downstream analysis. Treatment recommendations are generated through a Retrieval-Augmented Generation (RAG) architecture integrating WHO Essential Medicines guidelines, Federal Ministry of Health (FMOH) protocols, NIH MedlinePlus, and OpenFDA resources. Output reliability is improved through deterministic description generation, a three-tier language refinement pipeline, and hallucination detection algorithms, while Supabase manages authentication and interaction history. Evaluation results show strong performance, achieving 89% Top-3 accuracy, low hallucination rates, and high linguistic reliability, demonstrating the effectiveness of the proposed hybrid deterministic-RAG framework for multilingual healthcare support in low-resource African languages. Read more
    Keywords:Natural Language ProcessingMultilingual Medical DiagnosisNigerian Indigenous LanguagesLarge Language ModelsRetrieval-Augmented GenerationHealth Information System.