Academic Libraries are indeed lakes of mental energy. This Repository is a digital service that collects, preserves, and distributes digital material.
Communities in AUA iRepository
Select a community to browse its collections.
- Pan-African Journal for Health and Environmental Science (AJHES) The Pan-African Journal of Education and Social Sciences (PAJES) Pan African Journal of Theology (PAJOT)
- «
- 1 (current)
- 2
- 3
- »
Recent Submissions
Burnout among Faculty Members in Adventist Higher Institutions of Learning in Sub-Saharan Africa.
(International journal of research and innovation in social science (IJRISS), 2026-09-01) Mahlon Juma Nyongesa
This study investigated burnout using a quantitative descriptive design with a sample of 130 faculty members.
Data from a self-constructed questionnaire were analyzed using SPSS 27 and SmartPLS 4.0 for statistical
treatment. The faculty members experienced a high level of reduced professional efficacy but lower levels of
exhaustion and cynicism. In terms of age, the younger faculty members were more vulnerable to exhaustion,
reduced professional efficacy, and cynicism. Being male or female made no difference in the experience of
burnout. Further, the faculty members who work from home more than 80% of the time face higher levels of
burnout than those working from home 2 - 3 days a week and more than 80% in the office. For future research,
the study recommends the following.
For future research, a convergent parallel design mixed-methods approach could complement personal and
organizational factors. Not only should standardized and validated instruments such as the Maslach Burnout
Inventory be used to enhance reliability, but also the sample size should be expanded to include different
Adventist universities across Sub-Saharan African countries to improve generalizability. Changes in burnout
over time and identifying causal relationships would require a longitudinal research design. Future research
would look at how variables such as workload, organizational support, leadership style, job satisfaction, and
mental health resources affect burnout.
Psychopathic Experiences Among Faculty Members in Adventist Higher Institutions of Learning in Sub-Saharan Africa.
(International journal of research and innovation in social science (IJRISS), 2026-08-06) Mahlon Juma Nyongesa
This study sought to investigate the presence of psychopathic behaviors among faculty members using a
quantitative descriptive design with a sample of 130 faculty members. Data from a self-constructed questionnaire
were analyzed using SPSS 27 for statistical treatment. Faculty members demonstrated low levels of psychopathic
behaviors. This is attributed to their religious value system and the integration of faith in learning and teaching.
Being aged 18 – 44 years or aged 45 – 64 does not make one more vulnerable to psychopathic experiences.
Regardless of age, the psychopathic experiences are the same. Being a faculty member or HOD/Dean does not
make a difference in psychopathic behaviors. Any university faculty job level is vulnerable to psychopathic
behaviors. The One-way ANOVA test for a significant difference showed that the psychopathic behaviors of
faculty members across the Divisions do not significantly differ, as they adhere to the same education system and
share religious values. A phenomenological study would spell out the lived experiences. A convergent parallel
design could complement personal and organizational factors. Besides, the study could expand the sample size
to include public institutions across Sub-Saharan African countries and use standardized and validated
instruments to enhance reliability and improve generalizability. An examination of the influence of organizational
support, leadership style, and mental health resources on psychopathic experiences would be ideal.
Techniques and Tools for Information Extraction: Application to Social Media
(Computational Semantics IntechOpen, 2025-10) Lossan Bonde; Severin Dembele
This chapter presents a comprehensive and systematic review of the various tech
niques and tools used for information extraction (IE), focusing on social media. The
aim of the review is triple: (1) identify the techniques and tools used for IE applied to
social media, with a recommendation on when to use these techniques and tools; (2)
determine what applications along with the social networks use IE from social media;
and (3) identify the challenges associated with IE from social media. We combined
Kitchenham and the PRISMA methodologies to conduct the systematic review. Guided
by a review protocol and quality assessment, 58 papers were selected and analysed.
This review highlights the potential of social media information extraction, empha
sizing the central role of Machine Learning alongside emerging techniques like trans
formers. Applications span sentiment analysis, health, security, marketing, and
misinformation detection. Twitter dominates research, though other platforms are
studied. Key challenges include ethics, privacy, data scarcity, accuracy, and computa
tional costs, necessitating refined methods and ethical focus.
Improving Credit Card Fraud Detection with Ensemble Deep Learning-Based Models: A Hybrid Approach Using SMOTE-ENN
(Journal of Computing Theories and Applications (JCTA), 2025-02-12) Lossan Bonde; Abdoul Karim Bichanga
Advances in information and internet technologies have significantly transformed the business environment, including the financial sector. The COVID-19 pandemic has further accelerated this
digital adoption, expanding the e-commerce industry and highlighting the necessity for secure online
transactions. Credit Card Fraud Detection (CCFD) stands critical as the prevalence of fraudulent activities continues to rise with the increasing volume of online transactions. Traditional methods for
detecting fraud, such as rule-based systems and basic machine learning models, tend to fail to keep
pace with fraudsters' evolving tactics. This study proposes a novel ensemble deep learning-based approach that combines Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and
Multilayer Perceptron (MLP) with the Synthetic Minority Oversampling Technique and Edited Nearest
Neighbors (SMOTE-ENN) to address class imbalance and improve detection accuracy. The method
ology integrates CNN for feature extraction, GRU for sequential transaction analysis, and Multilayer
Perceptron (MLP) as a meta-learner in a stacking framework. By leveraging SMOTE-ENN, the proposed approach enhances data balance and prevents overfitting. With synthetic data, the robustness
and accuracy of the model have been improved, particularly in scenarios where fraudulent examples
are scarce. The experiments conducted on real-world credit card transaction datasets have established
that our approach outperforms existing methods, achieving higher metrics performance.
Challenges of recommender systems in finance and banking: a systematic review
(IAES International Journal of Artificial Intelligence (IJ-AI), 2025) Lossan Bonde; Abdoul Karim Bichanga
Recommender systems are widely applied in various domains, including
e-commerce, marketing, and education. Despite their popularity,
recommender systems are not widely used in finance and banking. This
paper aims to identify the challenges associated with using recommender
systems in finance and banking and recommend directions for future
research. Using a systematic literature review (SLR) method, 52 papers were
selected and analyzed. A three-step process was used to make the selection.
First, a keyword search was made to identify a seed list of sources. A
snowball technique with specific inclusion and exclusion criteria was
applied to expand the list. Finally, a quick study was made to produce the
final list of sources to consider. Through the study of the 52 relevant papers,
three main challenges: i) transparency, ethics, and data privacy; ii) handling
complex content information and accounting for multiple user behaviors;
and iii) explainability of AI models were identified. This study has
established the barriers to adopting recommender systems in the finance and
banking industry. Specific subjects of concern identified include cold-start
problems, personalization, fraud detection, transparency, and data privacy.
The study recommends further research leveraging advanced machine
learning models and emerging technologies to fill the gap.