Classifying Students Engagement in Computer Games using Linear Discriminant Analysis

Linear Discriminant Analysis can be used to determine which variable discriminates between two or more classes, and to derive a classification model for predicting the group membership of new observations. For each of the groups, LDA assumes the explanatory variables to be normally distributed with equal covariance matrices. The simplest LDA has two groups. To discriminate between them, a linear discriminant function that passes through the centroids of the two groups can be used. The study used Linear Discriminant Analysis in classifying student as addicted or non-addicted in computer games. The study conducted a survey in the form of questionnaire to the students who are playing computer games and a student in Mindanao University of Science and Technology (MUST). Young Diagnostic Test (eight-item questionnaire) was adopted and used Likert Scale to answer the survey questionnaire. The researcher was able to classify 100 students by using Linear Discriminant Analysis. It was found out that 61 out of 63 or 96.83 % is correctly classified as non-addicted and 35 out of 37 or 94.59 % is correctly classified as addicted to computer games. Moreover, the study has 4.29 % of average misclassification probability which implies that the Linear Discriminant Analysis performs better in classifying behavioral addiction. The study further showed that the students in MUST can manage their time properly as to when to study and when to play computer games as part of their recreational past time.