Implementation of Mechanical Learning Simple Linear Regression Accuracy Level of Mobile Legend Game Addiction for STMIK Kaputama Students

Abstract

This study aims to apply the Simple Linear Regression algorithm in measuring the accuracy of the addiction level of the Mobile Legend game based on the GAS (Game Addict Scale) scale. GAS is a scale used to assess a person's level of gaming addiction, which consists of several scoring items with various indicators of addiction. In this study, data was collected from a group of respondents who had filled out the GAS questionnaire. The value of the GAS scale is used as an independent variable (X) and the level of addiction to the Mobile Legend game is used as a dependent variable (Y). The method used is Simple Linear Regression, where a model will be developed to predict the level of addiction based on the GAS scale. The collected data is divided into two sets: a training set and a test set. The model is built using a training set and then tested using a test set to evaluate its accuracy. The results show that the Simple Linear Regression model is able to provide a fairly accurate prediction of the level of addiction to Mobile Legend games based on the GAS scale. Accuracy evaluations are performed using metrics such as Mean Squared Error (MSE) and R-squared (R²). The evaluation results show that the model has a low MSE value and a high R² value, which indicates that the independent variable (GAS scale) has a significant linear relationship with the dependent variable (Mobile Legend game addiction level). The Simple Linear Regression Algorithm can be used as an effective predictive tool to measure the level of game addiction based on the GAS scale. This research contributes to understanding the relationship between the GAS scale and game addiction, as well as opens up opportunities for further research in developing more complex and accurate prediction models.