Full Journal Issue

Story Points Prediction: Harnessing the Capability of Natural Language Processing to Enhance the Productivity of Agile Teams

Aris L. Parayno^1,2 and Mengvi P. Gatpandan²

¹Finastra Philippines, Pasig City, Metro Manila, Philippines

²College of Science and Computer Studies, De La Salle University – Dasmariñas, Dasmariñas, Cavite, Philippines

ABSTRACT

The financial industry demands highly stable and reliable software systems, as any disruption can significantly impact operations. Financial Technology (FinTech) firms address this need through advanced software development and maintenance processes. A critical component is issue tracking, which generates large volumes of unstructured data. This complexity slows defect sizing, traditionally performed by experts who assign story points (SP) based on complexity, effort, and risk. Manual SP estimation is time-consuming and dependent on expertise, creating bottlenecks. To overcome these challenges, this study proposes an automated machine learning (ML) approach. Using Term Frequency–Inverse Document Frequency to quantify textual data and the Random Forest algorithm for prediction, the model effectively estimates SP values. Random Forest achieved the highest accuracy among tested classification algorithms, demonstrating its suitability for this task. Despite challenges such as data quality, scalability, and integration with existing systems, ML offers significant potential to streamline defect sizing and enhance productivity. Future work may explore deep learning, real-time processing, automated data cleaning, and user-friendly interfaces to further improve accuracy and efficiency. This research underscores ML’s role in meeting the demanding requirements of financial software development and optimizing operational performance.

Keywords: Data Mining, Natural Language Processing (NLP), Machine learning (ML), Term Frequency-Inverse Document Frequency, Random Forest

Cite this Article:

A.L. Parayno & M.P. Gatpandan, “Story Points Prediction: Harnessing the Capability of Natural Language Processing to Enhance the Productivity of Agile Teams,” J. Eng. Comput. Tech., vol. 3 no. 1, pp. 1-8, Feb. 2025.

A Sentiment Analysis of Application Reviews on SHEIN using Naïve Bayes and Support Vector Machine

Fritz William Acebes, Katherine Cristal, Hannah Czarielle Luzande, Rolando Barrameda, Josephine Eduardo, Emelyn Mayuga, and Maryli Rosas

College of Science and Computer Studies, De La Salle University – Dasmariñas, Dasmariñas, Cavite, Philippines

ABSTRACT

This paper aims to compare the performance of two machine learning algorithms – Naïve Bayes and Support Vector Machine (SVM) – in classifying user reviews of the SHEIN application on Google Play as either positive or negative. The study utilized text processing techniques including tokenization, removal of stopwords, and other natural language processing methods. User review data was collected through web scraping and stored in CSV format. The classification performance of both algorithms was evaluated, with results showing that the Naïve Bayes classifier achieved a higher accuracy rate of 97% compared to SVM’s 84.8%. The findings highlight the potential of sentiment analysis as a tool for platform managers to extract user insights, improve service quality, and guide product development, while also informing consumers about general user perception of the app and its offerings.
 

Keywords: ecommerce, SHEIN, Google Play, Apparel

Cite this Article:

F.W. Acebes, K. Cristal, H.C. Luzande, R. Barrameda, J. Eduardo, E. Mayuga, & M. Rosas, “A Sentiment Analysis of Application Reviews on SHEIN using Naïve Bayes and Support Vector Machine,” J. Eng. Comput. Tech., vol. 3 no. 1, pp. 9-20, Feb. 2025.

ReVibe: A Multimodal Affective Personalized Music Recommender For User Wellbeing

Avin Nicolo R. Robles, Matthew H. Lumugdang, Matthew S. Reniva, and Tita R. Herradura

College of Science and Computer Studies, De La Salle University – Dasmariñas, Dasmariñas, Cavite, Philippines

ABSTRACT

Music is relevant to an individual’s wellbeing as it can influence stress reduction, sleep and mood enhancements, and emotions. With the integration of machine learning, the overall wellness of the listener can be enhanced through key-curated personalized song playlists based on the listener’s preferences. With that, the study developed ReVibe as a multimodal affective personalized music recommender web app designed for user wellbeing. The app utilizes facial expressions and text for song recommendations based on their current emotion. A variety of features such as stress relief, sleep improvement, and environment-based music recommendations were added to enhance the user-experience in the web app. Models such as CNN for Face Emotion Recognition (also known as FER) and a hybrid CNN-SVM model for Text Emotion Recognition (also known as TER), were used, and their predictions were combined with decision level fusion to provide the main emotion for the curated music playlist. The model achieved an accuracy score of 90% with a 43/57 split favored through text. The web app also received positive ratings based on its function, usability, and safety. Overall, the study provided insights and improvements for multimodal music recommenders and its importance towards the enhancement of users’ wellbeing.
 

Keywords: CNN, Decision level fusion, Machine learning, Multimodal, SVM

Cite this article:

A.N.R. Robles, M.H. Lumugdang, M.S. Reniva, & T.R. Herradura, “ReVibe: A Multimodal Affective Personalized Music Recommender For User Wellbeing,” J. Eng. Comput. Tech., vol. 3 no. 1, pp. 21-36, Feb. 2025.

A Comparative Study in Synchronous and Asynchronous Learning during the COVID-19 Pandemic of College Students using Regression Analysis

Fritz William Acebes, Katherine Cristal, Hannah Czarielle Luzande, Rolando Barrameda, Josephine Eduardo, Emelyn Mayuga, and Maryli Rosas

College of Science and Computer Studies, De La Salle University – Dasmariñas, Dasmariñas, Cavite, Philippines

ABSTRACT

This paper discusses the use of e-learning modes, specifically synchronous and asynchronous learning, for college students during the COVID-19 pandemic. The aim is to compare and predict the effectiveness of these learning modes by analyzing students’ General Weighted Average (GWA) in relation to the time spent in each mode. The independent variables are the number of hours spent in synchronous and asynchronous learning and associated student experiences (e.g., perceived usefulness, ease of use, intention to adopt). The dependent variable is the students’ academic performance measured via GWA. The researchers surveyed college students from De La Salle University- Dasmarinas (DLSU-D) (N=308) and some students outside of the university (N=93) to examine whether there is a significant difference in students’ grades based on how long they attend their synchronous and asynchronous classes. Data were collected after the last batch of the fully online learning model, which was the 2nd semester of the 2021-2022 school year.
 

Keywords: Online Learning mode, Synchronous Learning, Asynchronous Learning, Machine Learning, Regression Analysis, Simple Linear Regression, General Weight Average

Cite this Article:

F.W. Acebes, K. Cristal, H.C. Luzande, R. Barrameda, J. Eduardo, E. Mayuga, & M. Rosas, “A Comparative Study in Synchronous and Asynchronous Learning during the COVID-19 Pandemic of College Students using Regression Analysis,” J. Eng. Comput. Tech., vol. 3 no. 1, pp. 37-47, Feb. 2025.

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)