<![CDATA[Smartphone display modes (dark mode and light mode) play an important role in visual comfort, especially in relation to the risk of digital eye strain due to intensity of use and lighting conditions. This study aims to optimize the Naïve Bayes algorithm to predict display mode preferences based on users' visual ergonomics factors. Data were collected through an online survey of 283 smartphone users using purposive and convenience sampling. Seven variables were used as features, namely age, gender, duration of use, dominant time of use, purpose of use, screen type, and lighting conditions, with display mode preference as the target label. The study built two models, namely the baseline Naïve Bayes and the optimal model. Optimization was carried out by balancing the data with the Synthetic Minority Oversampling Technique for Nominal (SMOTEN) and adjusting the alpha hyperparameter using GridSearchCV. The evaluation results showed that the baseline model achieved an accuracy of 68.42% with a light mode class recall of 0.57. After optimization, the accuracy increased to 70.18% and the light mode recall rose to 0.71, indicating an improvement in the model's ability to recognize minority classes and reduce prediction bias. This study shows that SMOTEN optimization and hyperparameter tuning effectively improve the model's sensitivity to user preferences and have the potential to support the development of adaptive interfaces that automatically adjust the display mode to improve user visual comfort.]]>
