Stress is everyone's concern in the academic life of students. However, stress elevates due to several factors, including academic demands, family, and social realities. More recently, due to the COVID-19 pandemic, several universities shifted to online modality, which may contribute to students' academic stress considering its complex requirements. To date, no study has been conducted to examine the perceived academic stress of students in Philippine higher education institutions. Thus, this paper aims to develop stress prediction models using machine learning through a classification approach based on student's perceived academic stress (PAS) scale survey responses. Results show that most students have high to very high perceived academic stress in both male and female respondents. Also, results show that decision tree (91%), naïve bayes (94%), support vector machine (95%), logistics regression (90%), and k-nearest neighbors (91%) have comparable classification performance. Furthermore, this study found that the difficulty of examination, unrealistic expectations from the teacher, examination time, excessive workload, and weakness of character contribute to the perceived academic stress of students. This study confirms the potential of machine learning to classify students' academic stress. This work presents some contributions and practical recommendations on academic stress experienced by students.

With the rise of human-centric technologies such as social media platforms, the amount of hate also continues to grow proportionally with the increasing number of users worldwide. TikTok is one of the most-used social media platforms due to its feature that allows users to express themselves via creating and sharing short-form videos based on any desired topic and content. In addition, it has also become a platform for political discourse and mudslinging as users can freely express an opinion and indirectly debate with random people online. In this study, we propose the use of BERT, a complex bidirectional transformer-based model, for the task of automatic hate speech detection from speech transcribed from Tagalog TikTok videos. Results of our experiments show that a BERT-based hate speech classifier scores 61% F1. We also extended the task beyond several algorithms such as LSTM, Naïve Bayes, and Decision Tree and found out that traditional methods such as a simple Bernoulli Naïve Bayes approach remain at par with the BERT model.

In the past years, the Philippines recorded different disasters in diverse parts of the archipelago. The most frequent natural disasters were floods and storms that bring hazards to the people. The country has high level of exposure to hydro-meteorological hazards due to its geography. Because of the frequency, intensity, and variability of the hazards the government is compelled to adopt disaster risk reduction and management and climate change adaptation. In this study, we developed a web-based application for Relief and Casualty Monitoring and Early Warning System for Local Government Units in the Philippines tested in two case sites in the Philippines. Results show that the requirements set by the user were met. The overall evaluation shows that the system is useful in addressing some of the findings of the commission on audit assessment report in helping the local government unit in the Philippines in early warning for its constituents.

Crying is one of the means by which they express their emotional, psychological and physiological states. This paper investigates if audio features specifically the Mel Frequency Cepstral Coefficient (MFCC) & Linear Prediction Cepstral Coefficient (LPCC) are enough to classify the infants' physiological states such as hunger, pain and discomfort. To determine these physiological states, we recorded the cry of some infants who were immunized. The data for hunger and discomfort were recorded in the infants' house. The results showed that the audio features can classify an infant's physiological state. We used three classification algorithms, Decision Tree (J48), Neural Network and Support Vector Machine in developing the infant physiological model. To evaluate the performance of the infant physiological state model, Precision, Recall and F-measure were used as performance metrics. We found out that Decision Tree and Multilayer Perceptron performed better for the given dataset with correctly classified instances ranging from 87.64% to 90.80 with an overall kappa statistic ranging from 0.47 - 0.64.