This study investigates stressors in higher education, focusing on their impact on students and faculty at Universidad Politécnica Salesiana (UPS) and using eight years of comprehensive data. Employing data mining techniques, the research analyzed enrollment, retention, graduation, employability, socioeconomic status, academic performance, and faculty workload to uncover patterns affecting academic outcomes. The study found that UPS exhibits a stable educational system, maintaining consistent metrics across student success indicators. However, the COVID-19 pandemic presented unique stressors, evidenced by a paradoxical increase in student grades during heightened faculty stress levels. This anomaly suggests a potential link between academic rigor and faculty well-being during systemic disruptions. Stressors affecting students directly correlated with reduced academic performance, highlighting the importance of early detection and intervention. Conversely, faculty stress was reflected in adjustments to grading practices, raising questions about institutional pressures and faculty motivation. These findings emphasize the value of proactive data analytics in identifying stress-induced anomalies to support student success and faculty well-being. The study advocates for further research on faculty burnout, motivation, and institutional strategies to mitigate stressors, underscoring the potential of data-driven approaches to enhance the quality and sustainability of higher education ecosystems.
This paper presents a scalable and low-cost Retrieval Augmented Generation (RAG) architecture designed to enhance learning in university-level courses, with a particular focus on supporting students from economically disadvantaged backgrounds. Recent advances in large language models (LLMs) have demonstrated considerable potential in educational contexts; however, their adoption is often limited by computational costs and the need for stable broadband access, issues that disproportionately affect low-income learners. To address this challenge, we propose a lightweight, mobile, and friendly RAG system that integrates the LLaMA language model with the Milvus vector database, enabling efficient on device retrieval and context-grounded generation using only modest hardware resources. The system was implemented in a university-level Data Mining course and evaluated over four semesters using a quasi-experimental design with randomized assignment to experimental and control groups. Students in the experimental group had voluntary access to the RAG assistant, while the control group followed the same instructional schedule without exposure to the tool. The results show statistically significant improvements in academic performance for the experimental group, with p < 0.01 in the first semester and p < 0.001 in the subsequent three semesters. Effect sizes, measured using Hedges g to account for small cohort sizes, increased from 0.56 (moderate) to 1.52 (extremely large), demonstrating a clear and growing pedagogical impact over time. Qualitative feedback further indicates increased learner autonomy, confidence, and engagement. These findings highlight the potential of mobile RAG architectures to deliver equitable, high-quality AI support to students regardless of socioeconomic status. The proposed solution offers a practical engineering pathway for institutions seeking inclusive, scalable, and resource-efficient approaches to AI-enhanced education.
The increasing adoption of video-based instruction and digital assessment in higher education has reshaped how students interact with learning materials. However, it also introduces cognitive and behavioral biases that challenge the accuracy of self-perceived learning. This study aims to bridge the gap between perceived and actual learning by investigating how illusion learning—an overestimation of understanding driven by the fluency of instructional media and autonomous study behaviors—affects cognitive performance in university mathematics. Specifically, it examines how students’ performance evolves across Bloom’s cognitive domains (Understanding, Application, and Analysis) from midterm to final assessments. This paper presents a data-driven investigation that combines the theoretical framework of illusion learning, the tendency to overestimate understanding based on the fluency of instructional media, with empirical evidence drawn from a structured and anonymized dataset of 294 undergraduate students enrolled in a Linear Algebra course. The dataset records midterm and final exam scores across three cognitive domains (Understanding, Application, and Analysis) aligned with Bloom’s taxonomy. Through paired-sample testing, descriptive analytics, and visual inspection, the study identifies significant improvement in analytical reasoning, moderate progress in application, and persistent overconfidence in self-assessment. These results suggest that while students develop higher-order problem-solving skills, a cognitive gap remains between perceived and actual mastery. Beyond contributing to the theoretical understanding of metacognitive illusion, this paper provides a reproducible dataset and analysis framework that can inform future work in learning analytics, educational psychology, and behavioral modeling in higher education.
This paper presents an open, anonymized dataset of academic service requests collected before and after an administrative process redesign in a multi-campus university in Ecuador. The dataset was extracted from the Sistema Nacional Académico and covers two consecutive six-month periods: PERIOD_1, representing the original processes, and PERIOD_2, representing the redesigned processes. It contains 432 aggregated records corresponding to 97,809 requests across three pseudonymized campuses, 25 request types, and 13 workflow states. Each record combines period, campus, request type, current state, and the aggregated request count, while reducing disclosure risk through aggregation and removal of identifiers. Descriptive analyses show that request volume increased by 14.03%, while the combined share of requests observed in the Approved and Processed Request states increased from 75.71% to 77.36%. At the common extraction snapshot, the proportion of requests observed in four institutionally defined undesirable workflow states decreased from 5.20% to 4.46%. The dataset, documentation, and reproducible analysis code are publicly available through Figshare and GitHub, supporting research on higher education administration, workflow analysis, institutional analytics, and process improvement.