Rice is a vital staple crop and an essential component of the diet in many Asian nations. Over the years challenges have arisen in rice farming due to the vulnerability of rice crops to attacks by more than 100 types of insects which can cause significant yield losses. This research focuses on predicting rice bug infestations in rice fields using data mining and machine learning techniques. Several machine learning algorithms including Decision Tree, Optimizable Discriminant, Naïve Bayes, Support Vector Machine, K-Nearest Neighbors, Ensemble, and Neural Network, were employed to analyzed patterns and build predictive models for rice pest infestations. The dataset spans from 2005 to 2019 and includes historical data, field observations, and interviews with agriculturists and farmers. The study aims to enhance understanding of the factors influencing rice bug infestations and to develop timely alert systems to minimize potential crop losses. Model performance was improved through the fine-tuning of hyperparameters, with training and evaluation conducted using an 80:20 data split and 10-fold cross-validation. The KNN and Ensemble models achieved the highest accuracy rates at 98.3%. These findings provide valuable insights for agricultural institutions and farmers in selected municipalities of Region IVA and may also be adapted for other crops with similar pest challenges using comparable parameters.

The proposed research aims to develop a hybrid learning analytics model that incorporates clickstream and sentiment mining techniques to accurately predict student retention in Learning Management Systems (LMS) in Manila-based HEIs. This proposed research aims to improve the limitations of single prediction modeling. The proposed research utilized a quantitative explanatory research design and was applied to undergraduate students taking general education courses. The proposed research utilized stratified sampling to select a total of 345 students. Clickstream and text-based interaction data were analyzed to obtain sequence and sentiment-based metrics to train the hybrid prediction model using Logistic Regression and XGBoost. The engagement tool was also able to reach Cronbach's alpha = 0.91, which is a good measure of internal consistency. This shows that the click-only model had an AUC of 0.78, but the hybrid model was enhanced to 0.84, with the top predictors being attempts at quizzes per week and negative sentiment ratio. This shows the importance of multimodal analytics in the improvement of early warning systems and proactive interventions. The implication of this can be seen in the administration of the institution and the academic support, which is a basis for evidence-based retention and fairness-based predictive models in Philippine Higher Education.

As cybersecurity threats increasingly impact business operations, equipping future managers with foundational digital security skills is essential. This study presents the design and evaluation of an AI-personalized gamified website aimed at enhancing cybersecurity awareness among business management students. The platform integrates intelligent agents to adapt content difficulty, provide real-time feedback, and personalize learning paths based on user behavior. Gamification elements, including scenario-based challenges, progress badges, and interactive simulations, are embedded to improve engagement and retention. A pilot implementation across two higher education institutions measured learning outcomes, engagement metrics, and usability. Results indicate significant improvements in students’ cybersecurity knowledge, decision-making accuracy, and motivation compared to traditional instruction. The study contributes a scalable framework for integrating AI and gamification into business education, aligning with the evolving demands of digital business environments.

In order to meet the need for scalability in academic advising in higher education settings while ensuring compliance, fairness, and privacy, we propose a governance-ready multi-agent reinforcement learning framework that aggregates the advantages of four highly specialized agents, namely, the Plan Validator, Risk Detector, Resource Recommender, and Conversational Advisor, which function collaboratively with a policy learner and under the supervision of a human. In a quasi-experimental mixed-methods study involving n = 345 participants from different departments, the system yielded a substantial improvement over the baseline in terms of efficiency and quality, where the turnaround time in academic advising was reduced by ≈60% or from 48.6 to 19.3 hours, while compliance was boosted by +11.3% and risk detection recall was enhanced by +0.12 or from 0.67 to 0.79. The stability of the learning process was satisfactory, with a normalized cumulative reward of +0.35 and around 1,200 episodes to converge. For the governance control, the effectiveness of the proofs was satisfactory, as the fairness gap reduced from 7.8% to 3.2%, while the privacy incidents remained zero even with continuous audits. In terms of evaluation, a mixed methods evaluation design was used, which included the performance records of the RL, ANOVA subgroup, and trust judgments to establish validity. From the findings, the MARL solution is technically viable, ethical, and feasible as an advisory mechanism in HEIs. Suggestions are made for future directions to investigate the solution's scalability and dynamic reward shaping for various policies.

Generative artificial intelligence (AI) presents new opportunities for enhancing blended and hybrid learning through adaptive and visually rich instructional materials. This study proposes a concise pedagogical framework for integrating AIgenerated visuals, produced using text-to-image tools such as Adobe Firefly and NanoBanana, into hybrid classroom instruction. By enabling rapid creation of customized visual content aligned with lesson objectives, these tools support diverse learning styles and conceptual understanding. A mixed-methods approach was employed, combining pre-test and post-test assessments, learning management system (LMS) engagement analytics, and qualitative feedback from students and faculty. Results indicate measurable improvements in student comprehension, time-on-task, and interaction rates when AI-generated visuals were incorporated into blended learning modules. Ethical considerations, including content accuracy, bias, and faculty readiness, were also examined. The study contributes a practical and scalable model for the responsible integration of AI-generated visuals into technologyenhanced learning environments.