John Heland Jasper C. Ortega et al., International Journal of Advanced Trends in Computer Science and Engineering, 9(1.3), 2020, 475 - 480 475 ABSTRACT Classifying tumors into benign and malignant take time and resources; sometimes it takes several radiologists and oncologists to diagnose if a tumor is malignant or benign, especially if features are hardly distinguishable to the human eye. To determine a way to automatically classify if a tumor is benign or malignant, the researchers developed a model using J48 decision tree algorithm to classify a tumor through analysis of cell features extracted by the X-cyt program. Based on confusion matrix analysis, the algorithm performed well by recording a 95 percent accuracy rate derived from confusion matrix analysis. Key words: Breast Cancer, Diagnosis, Diagnostics, Oncology, Pathology, Radiology 1. INTRODUCTION Most cancers in general are hard to diagnose, especially in its earlier stages, when left undiagnosed, the cancer, beginning from its primary origin, starts to proliferate to the immediate cells around the tumor before metastasizing to other parts of the body. Unfortunately, cancers are usually diagnosed during stage III or IV, when the patient experiences symptoms by which in the third stage, the cancer has already spread to immediate cells surrounding the tumor but not yet to distant organs. Addressing this problem leads to saving lives. With this, the researchers utilized the efficiency of machine learning algorithms particularly decision tree algorithms to extract hidden patterns that can be particularly useful in this domain. 1.1 Background of the Study Over the past decades, breast cancer is still one of the most common cancers [1]. Diagnosing whether a tumor is malignant is of utmost importance in order to provide the right treatment. Oncologists for one will never deny the benefit of having the technology to automatically classify breast cancer types within seconds, saving their time and providing more time for the patient’s treatment and recuperation. The importance of diagnosing the malignancy of cancers has led researchers to study the study of machine learning and deep learning including its application [13][2]. One of the key machine learning algorithms used in the prediction of cancer is decision tree algorithm. Decision trees classifies data into leaf nodes and internal nodes that are connected by branches, resembling an inverted tree, with the root node in the top most portion of the tree, all for the purpose of extracting useful information [3]. Although there have been numerous research validating the benefits of machine learning in the field of oncology, these papers must first undergo thorough validation before they are deployed into the healthcare industry. 1.2 Research Questions In this section, the following research questions are formulated. a. How to develop a model that will classify whether a tumor in the breast area is benign or malignant? b. How effective the develop model in terms of confusion matrix analysis? c. How effective the system as perceived by experts using ISO 9126 metrics? 1.3 Literature Reviews Data Mining is an area under computer science that deals with the applications of machine learning algorithms in order to develop data models that can be used for prediction, cluster and association analysis [4]. Knowledge Discovery in Databases (KDD) provides a step by step mechanism in order to generate useful patterns that can be used in different domains. The main steps of this methodology involve data preprocessing, modeling, An Analysis of Classification of Breast Cancer Dataset Using J48 Algorithm John Heland Jasper C. Ortega 1 , Michael R. Resureccion 2 , Lizel Rose Q. Natividad 3 , Emilsa T. Bantug 4 , Ace C. Lagman 5 , Shinji Robin Lopez 6 1 FEU Institute of Technology, Philippines, jcortega@feutech.edu.ph 2 University of the East, Philippines, resurreccion.michael@ue.edu.ph 3 San Beda University, Philippines, lnatividad@sanbeda.edu.ph 4 Nueva Ecija University of Science and Technology, Philippines, emilsa.bantug@neust.edu.ph 5 FEU Institute of Technology, Philippines, aclagman@feutech.edu.ph 6 FEU Institute of Technology, Philippines, srlopez@feutech.edu.ph ISSN 2278-3091 Volume 9, No.1.3, 2020 International Journal of Advanced Trends in Computer Science and Engineering Available Online at http://www.warse.org/IJATCSE/static/pdf/file/ijatcse7591.32020.pdf https://doi.org/10.30534/ijatcse/2020/7591.32020