Yetunde Folajimi

Dr. Yetunde Folajimi

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

5 December 2024
Verified
Conference Paper
Open access
YFYetunde Folajimi
Yetunde Folajimi
This study evaluates the effectiveness of four leading large language models (LLMs), GPT-3, GPT-4, GPT-4o, and BERT, in generating quiz questions for Java and Python programming courses. We aim to recognize how LLMs can effectively produce educationally valuable questions that meet specific pedagogical criteria, including technical precision, relevance to course objectives, linguistic clarity, and pedagogical appropriateness. Each model was prompted to generate 200 Java and 200 Python quiz questions, totaling 1600 unique questions. These questions are currently being evaluated based on both quantitative and qualitative assessments by a team of computer science educators. Preliminary findings suggest that GPT-4 outperforms BERT in terms of technical precision. Further analysis is ongoing to assess the performance of the models in generating contextually appropriate and educationally useful questions, offering insights into their potential integration into computer science curricula. This work seeks to contribute to the broader discourse on the utility of LLMs in educational settings, specifically within the scope of automated content creation to enhance teaching and assessment methodologies in computer science education.

1 December 2025 in Journal of Medical Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YFYetunde Folajimi
Yetunde Folajimi
Background: Despite a growing body of literature on fibromyalgia, a systematic understanding of thematic evolution and sentiment trends remains limited. This study addresses that gap by utilizing advanced computational methods in artificial intelligence (AI) and big data analytics to analyze 5,861 fibromyalgia-related abstracts from PubMed. The aim is to uncover dominant research themes, sentiment dynamics, and temporal trends in scientific focus, which can provide valuable meta-insights for future research and clinical strategies. Methods: The dataset was preprocessed normalization, tokenization, stop-word removal, and lemmatization. A document-term matrix was created using CountVectorizer, followed by Latent Dirichlet Allocation (LDA) topic modeling. Sentiment scores were calculated using Scikit-Learn. Statistical validation included chi-square testing and coherence score analysis to ensure model reliability. Results: Keyword frequency analysis revealed a strong emphasis on patient-centered research, pain management, and clinical studies. The LDA model, configured with five topics and evaluated with a coherence score of 0.52, identified core themes in fibromyalgia research: (I) treatment efficacy and sleep-related issues; (II) physical therapy and exercise; (III) symptom classification and chronicity; (IV) comparative studies with controls; and (V) gender-specific research. Sentiment analysis revealed 42% positive, 35% neutral, and 23% negative tones across the dataset. Temporal trends demonstrated notable peaks and declines in publication frequency, reflecting changes in research interest and technological advancements. Conclusions: Our findings highlight key shifts in fibromyalgia research, including a growing focus on patient-centered and interdisciplinary approaches, an increased application of non-pharmacological interventions, and the integration of big data and AI in medical research. The statistically significant findings contribute to evidence-based research and can inform future research directions, funding priorities, and clinical strategies.

27 April 2026 in Computers
Verified
Journal Article
Open access
PDF file
LSLev Sukherman
Lev Sukherman
YFYetunde Folajimi
Yetunde Folajimi
MKMarina Konkol
Marina Konkol
This paper investigates whether structured collaboration between multiple large language models (LLMs), each assigned a distinct cognitive role grounded in psychological theory, produces benefits beyond simple answer aggregation. We propose the Parallel Synthesis architecture, in which three cognitively specialized roles Analyzer (hierarchical decomposition), Creative (divergent thinking), and Critic (critical evaluation) process each task independently and in parallel, and a Synthesizer integrates their outputs into a final response. To evaluate collaborative reasoning, we introduce the Emergent Reasoning Score (ERS), a composite metric that separates perspective integration (Synthesis Effectiveness) from novel concept generation (Emergent Value). Experiments on the AI2 Reasoning Challenge (ARC-Challenge) (1172 questions) and and the Massive Multitask Language Understanding benchmark (MMLU) (1531 questions) show two consistent findings. First, the architecture achieves high Synthesis Effectiveness (SE=0.711–0.744), indicating reliable integration of all three cognitive perspectives. Second, Emergent Value remains low (EV=0.096–0.112), indicating that synthesis primarily recombines existing concepts rather than generating substantial novel content. A Majority Voting baseline achieves comparable or slightly higher answer accuracy than the Synthesizer on both benchmarks, showing that the architecture’s main contribution lies not in answer selection but in producing integrated reasoning traces that draw on multiple perspectives. These findings suggest that the practical value of cognitively grounded multi-agent architectures lies in reliable perspective integration, while ERS provides a reusable framework for distinguishing integration from genuinely novel reasoning in multi-agent LLM systems. The empirical results reported here constitute a pilot validation of the proposed framework on closed-form benchmarks, intended to establish a proof of concept and motivate larger-scale evaluation.

31 August 2026
Verified
Conference Paper
Open access
LSLev Sukherman
Lev Sukherman
YFYetunde Folajimi
Yetunde Folajimi
MKMarina Konkol
Marina Konkol

2 August 2026
Verified
Book Chapter
Closed access
PDF file
MGMartin Jimenez Gil
Martin Jimenez Gil
YFYetunde Folajimi
Yetunde Folajimi
SOSalem Othman
Salem Othman
LDLeon Deligiannidis
Leon Deligiannidis