Analyzing the Attitudes of Senior High School and College Students at De La Salle University - Dasmarinas Towards Blended Learning Using Naive Bayes Classifier

Trisha Mae l. Baylon, Janella Marie G. Masongsong, Svetlan D. Mauleon, Maryli F. Rosas, Josephine T. Eduardo, Emelyn D. Mayuga, and Rolando B. Barrameda

College of Information and Computer Studies, De La Salle University – Dasmarinas, City of Dasmarinas, Cavite, Philippines

ABSTRACT

When the COVID-19 pandemic happened, the Philippines faced waves of lockdown to avoid the spread of the disease. To continue with the delivery of education; several universities were required by the government to apply blending learning schemes. With that, the study aims to explore the blended learning experience of college and senior high school students at De La Salle University- Dasmariñas involving 772 randomly selected students as the respondents. Descriptive correlation and Naive Bayes Classifiers were used in the sentiment analysis on the experience of the students. The findings revealed that students were generally satisfied with hands-on activities, peer collaboration, and instructor interaction during onsite classes. However, difficulties were noted in class scheduling, particularly when online and onsite sessions occurred on the same day, causing fatigue. Students also cited challenges in online communication and focus. Sentiment analysis further highlighted a mix of positive and neutral expressions, reflecting both appreciation and concerns. Recommendations include restructuring class schedules to prevent overlap of onsite and online sessions in a single day, enhancing communication between instructors and students during online learning, and providing institutional support to reduce student fatigue. Furthermore, future studies are encouraged to employ advanced algorithms, such as SGDClassifier, and consider longitudinal approaches to capture how student sentiments evolve over time. 

Keywords: Blended learning, Naïve Bayes Classifier, Sentiment Analysis, Descriptive correlation

Cite this Article:

T.M.l. Baylon, J.M.G. Masongsong, S.D. Mauleon, M.F. Rosas, J.T. Eduardo, E.D. Mayuga, and R.B. Barrameda. "Supervised Machine Learning: An Approach in Predicting the Adaptability Level of Diverse Learners". Journal of Engineering, Computing and Technology, vol. 4 no. 1. Feb., 2026

EDULIFT: A Machine Learning–Powered Career and Learning Pathway Recommender System for Students and Out-of-School Youth in the Philippines

Ryan Justin Dancel and Jesse James Lavarro

De La Salle University – Dasmarinas, City of Dasmarinas, Cavite, Philippines

ABSTRACT

Career indecision remains a persistent challenge among Filipino students and out-of-school youth (OSY), largely due to limited access to structured career guidance services and the increasing complexity of educational and labor market pathways. Many learners are required to make critical decisions regarding academic programs, technical-vocational training, or immediate employment with minimal personalized support. Traditional career counseling approaches often rely on manual assessments, interviews, and subjective judgment, which may not consistently account for individual differences in skills, interests, educational background, and learning preferences. This study presents EduLift, a machine learning–powered career and learning pathway recommender system designed to provide data-driven and personalized recommendations for career tracks, higher education programs, and Technical Education and Skills Development Authority (TESDA) courses. EduLift employs Random Forest classification models trained on curated datasets of 1,500 samples aligned with the Philippine education system and workforce structure. The system is deployed as a web-based application that supports both user-facing recommendations and administrative data management. System evaluation was conducted using accuracy metrics, 10-fold cross-validation techniques, and usability feedback from target users. Results indicate that EduLift generates reliable and contextually relevant recommendations, achieving an overall accuracy of 92%, a precision of 93%, and an F1-score of 92%. These findings demonstrate consistent performance across multiple recommendation domains and suggest that machine learning–based guidance systems can effectively complement traditional counseling services by improving accessibility, consistency, and decision support, particularly for underserved populations such as out-of-school youth in the Philippines.

Keywords: Career recommendation, machine learning, educational technology, decision support systems

Cite this Article:

R.J. Dancel and J.J. Lavarro. "EDULIFT: A Machine Learning–Powered Career and Learning Pathway Recommender System for Students and Out-of-School Youth in the Philippines". Journal of Engineering, Computing and Technology, vol. 4 no. 1. Feb., 2026

IoT-Based Fire Detection and SMS Alert System with Real-Time Room Tracking for the ICT Building at De La Salle University–Dasmariñas

Joshua C. Dacasin, John Rey B. Garvez, Angelo B. Jimenez, Emelyn D. Mayuga

Computer Studies Department, De La Salle University – Dasmariñas, City of Dasmariñas, Philippines

ABSTRACT

One of the priorities of every educational institution is to ensure the safety and security of its students and personnel, particularly in preventing fire incidents that may threaten lives and property. The effectiveness of Emergency response measures is often determined by the speed and accuracy of hazard detection systems during critical incidents. Traditional fire alarms often lack real-time monitoring capabilities and precise location tracking. Hence, the modernization of these safety measures through automated communication is significant for minimizing property damage and improving emergency response efficiency. The use of Internet of Things (IoT) allows for the integration of environmental sensors to extract real-time data, which can be used to accelerate emergency response times and support early fire prevention. The main objective of this study is to develop an IoT-based fire detection and monitoring system designed to help prevent fire incidents through early hazard detection and automated alert notification. The study focuses on the application of an ESP32-based architecture through multi-sensor integration, specifically flame, smoke, gas, and temperature sensors, and the implementation of the PhilSMS API for automated alert dissemination. The system also utilizes web-based dashboard analytics and occupancy tracking through Passive Infrared (PIR) sensors to classify hazard severity and provide actionable insights for administrators. The system was developed through the integration of multiple sensors with the ESP32 microcontroller and evaluated through controlled fire simulation tests, where variations in smoke, heat, and flame presence were introduced to measure detection capability and SMS alert response time.

Keywords: fire detection, Internet of Things, ESP32, multi-sensor monitoring, SMS alerts, real-time monitoring, room occupancy tracking, web dashboard, PhilSMS API, and ISO/IEC 21823-1

Cite this Article:

J.C. Dacasin, J.R.B. Garvez, A.B. Jimenez, and E.D. Mayuga. " IoT-Based Fire Detection and SMS Alert System with Real-Time Room Tracking for the ICT ". Journal of Engineering, Computing and Technology, vol. 4 no. 1. Feb., 2026

Sentiment Analysis of Students’ Experiences with Blended  Learning and Traditional Learning Using Logistic Regression and Decision Tree

Lalaine Joy C. Bejarin, Francheska Christine C. Mojica, Samantha P. Sampot, Maryli F. Rosas, Josephine T. Eduardo, Rolando B. Barrameda, and Emelyn D. Mayuga

Computer Studies Department, De La Salle University – Dasmariñas, City of Dasmariñas, Cavite, Philippines

ABSTRACT

The goal of this study was to investigate the opinions of high school and college students about blended learning and traditional learning in the aftermath of the COVID-19 pandemic. The study relied on a survey administered through Google Forms to collect data from 1000 college and senior high school students from various institutions. The researchers conducted a sentiment analysis of the responses using Logistic Regression and Decision Tree as classifiers. The results of the study show that most of the students feel positively about traditional learning while most of the students expressed neutral sentiments towards blended learning. The researchers also found that demographic factors such as age, gender and location had an impact on the sentiments of the students towards blended and traditional learning. Overall, the study provided valuable insights on the perception of students towards blended learning and traditional learning after the COVID-19 post-pandemic, and information that can inform future policies and strategies for educational institutions to improve the quality of education with better policies and strategies. 

Keywords: COVID-19, pandemic, logistic regression, decision tree, blended learning, traditional learning, sentiment analysis, post-pandemic education 

Cite this Article:

L.J.C. Bejarin, F.C.C. Mojica, S.P. Sampot, M.F. Rosas, J.T. Eduardo, R.B. Barrameda, and E.D. Mayuga. "Sentiment Analysis of Students’ Experiences with Blended Learning and Traditional Learning Using Logistic Regression and Decision Tree". Journal of Engineering, Computing and Technology, vol. 4 no. 1. Feb., 2026

JOURNAL OF ENGINEERING, COMPUTING AND TECHNOLOGY

The Journal of Engineering, Computing and Technology (JECT) is a scholarly peer-reviewed, and academic research journal for engineers, computer scientist, academicians, and research scholars aiming to publish innovative, state of the art results coming from research and advances in different aspects of engineering, architecture, computer science and information technology.  JECT is dedicated to the dissemination of advanced technologies that will be beneficial to professionals and academic researchers. It is a bi-annual publication published by the University Research Office, De La Salle University-Dasmariñas.

The journal is governed by an editorial board whose members specialize in each of the mentioned disciplines.  The editor in chief is elected by the members of the editorial board.

Editorial Board

Editor-in-Chief

Maryli F. Rosas, DIT (Computer Science, De La Salle University-Dasmariñas)

Associate Editor

Ma. Cristina A. Macawile, PhD (Engineering, De La Salle University- Dasmariñas)

Managing Editor

Mr. Jaime Zeus C. Agustin (University Research Office, De La Salle University-Dasmariñas)

Members

Paulino H. Gatpandan, DIT (Computer Science, De La Salle University- Dasmariñas)

Maryjoie A. Lituanas, MSES (Engineering, De La Salle University- Dasmariñas)

Mengvi P. Gatpandan, DIT (Computer Science, Jose Rizal University, Mandaluyong City)

Daniel Dasig Jr., PhD (Field, Change Management Engineer, TELUS Communication Inc., Canada)

Nestor Tiglao, PhD (Electrical and Electronics Engineering Institute, University of the Philippines – Diliman)

Atty. Rudolph Val F. Guarin (Field, FGNG Law Office)

Prof. Sonia M. Pascua (Field, Drexel University, United States of America)

Brojo Kishore Mishra, PhD (Department of CSE, School of Engineering, GIET University, Gunupur, India)

Valentina Emilia Balas, PhD (Automation and Applied Informatics, Intelligent Systems Research, University of Arad, Romania)

JOURNAL OF ENGINEERING, COMPUTING AND TECHNOLOGY

The Journal of Engineering, Computing and Technology (JECT) is a scholarly peer-reviewed, and academic research journal for engineers, computer scientist, academicians, and research scholars aiming to publish innovative, state of the art results coming from research and advances in different aspects of engineering, architecture, computer science and information technology.  JECT is dedicated to the dissemination of advanced technologies that will be beneficial to professionals and academic researchers. It is a bi-annual publication published by the University Research Office, De La Salle University-Dasmariñas.

The journal is governed by an editorial board whose members specialize in each of the mentioned disciplines.  The editor in chief is elected by the members of the editorial board.

Editorial Board

Editor-in-Chief

Maryli F. Rosas, DIT (Computer Science, De La Salle University-Dasmariñas)

Associate Editor

Ma. Cristina A. Macawile, PhD (Engineering, De La Salle University- Dasmariñas)

Managing Editor

Mr. Jaime Zeus C. Agustin (University Research Office, De La Salle University-Dasmariñas)

Members

Paulino H. Gatpandan, DIT (Computer Science, De La Salle University- Dasmariñas)

Maryjoie A. Lituanas, MSES (Engineering, De La Salle University- Dasmariñas)

Mengvi P. Gatpandan, DIT (Computer Science, Jose Rizal University, Mandaluyong City)

Daniel Dasig Jr., PhD (Field, Change Management Engineer, TELUS Communication Inc., Canada)

Nestor Tiglao, PhD (Electrical and Electronics Engineering Institute, University of the Philippines – Diliman)

Atty. Rudolph Val F. Guarin (Field, FGNG Law Office)

Prof. Sonia M. Pascua (Field, Drexel University, United States of America)

Brojo Kishore Mishra, PhD (Department of CSE, School of Engineering, GIET University, Gunupur, India)

Valentina Emilia Balas, PhD (Automation and Applied Informatics, Intelligent Systems Research, University of Arad, Romania)