<![CDATA[In the digital work environment, long working hours and blurred work-life boundaries have become increasingly common, raising concerns about employees’ mental health, particularly among Generation Z. This study examines how Generation Z perceives working hours and their impact on mental health using social media–based sentiment analysis. Data were collected from 848 TikTok videos posted between 2023 and 2025, consisting of captions and comments related to work-related stress. Sentiment classification was performed using machine learning models, namely Multinomial Naïve Bayes, Support Vector Machine (SVM), and Multilayer Perceptron (MLP). Text representation employed Bag-of-Words and Term Frequency–Inverse Document Frequency (TF-IDF). The results indicate that positive and negative sentiments dominate discussions, reflecting strong emotional responses to working-hour pressure, while neutral sentiment remains difficult to identify. Among the evaluated models, SVM with a radial basis function kernel achieved the best overall performance. These findings highlight the potential of TikTok based sentiment analysis for understanding Generation Z’s mental health in digital work contexts.]]>
Copyrights © 2026
