Alfilia Hilda Rahmatika, Bella Okta Sari Miranda, Imam Adiyana, Isyiffah Falujjah Anugrah Putri

Analyzing Generation Z's Sentiment on Working Hours and Mental Health Using IndoBERT: Evidence from TikTok Discussions

Introduction

Analyzing generation z's sentiment on working hours and mental health using indobert: evidence from tiktok discussions. Analyze Gen Z's sentiment on working hours & mental health using IndoBERT on TikTok data. Discover negative sentiment, highlighting the need for flexible policies & mental health support.

Abstract

Working hours exceeding recommended limits may increase burnout, psychological stress, and sleep disturbances, particularly among Generation Z, who highly value mental health and work-life balance. Although public opinions on this issue are increasingly expressed on social media, most existing studies rely on conventional machine learning methods or lexicon-based labeling, which are less effective at capturing contextual meaning and linguistic nuance in informal social media text. To address this gap, this study proposes a transformer-based sentiment analysis framework that employs a fine-tuned BERT-based Multilingual model as the primary sentiment classifier, rather than merely as an automatic labeling tool, to analyze Generation Z's sentiment toward working hours and mental health based on TikTok comments. A total of 2,203 comments were collected through web scraping and processed using cleaning, normalization, tokenization, and BERT-based zero-shot sentiment labeling before being used to fine-tune the classification model. The model was evaluated using accuracy, precision, recall, and F1-score. The results indicate that negative sentiment dominated the dataset (41.13%), followed by positive (37.49%) and neutral (21.38%) sentiments. Frequently occurring terms, such as working hours, work, and resigning, suggest that users' concerns mainly relate to long working hours and the intention to leave their jobs. The fine-tuned model achieved excellent classification performance, although a gap between training and validation performance indicates the need for improved generalization. These findings demonstrate that BERT-based sentiment analysis can provide valuable insights for organizations, policymakers, and human resource practitioners in developing more flexible working-hour policies and mental health support programs tailored to Generation Z.

Review

The paper "Analyzing Generation Z's Sentiment on Working Hours and Mental Health Using IndoBERT: Evidence from TikTok Discussions" addresses a highly pertinent and contemporary issue: the impact of working hours on the mental health of Generation Z. Recognizing Gen Z's strong emphasis on work-life balance and mental well-being, the authors highlight a critical gap in existing research, which often relies on less effective conventional machine learning or lexicon-based methods for analyzing nuanced social media discourse. This study's primary contribution lies in its innovative use of a transformer-based sentiment analysis framework, specifically employing a fine-tuned BERT-based Multilingual model (IndoBERT) as the central sentiment classifier, moving beyond its typical application as merely an automatic labeling tool. The methodological approach involves the collection of 2,203 TikTok comments, a rich and informal data source highly relevant to Gen Z's spontaneous expressions. The rigorous data preprocessing steps, including cleaning, normalization, and tokenization, followed by BERT-based zero-shot sentiment labeling prior to fine-tuning, demonstrate a robust framework for handling informal text. The fine-tuned model's performance was evaluated using standard metrics (accuracy, precision, recall, F1-score), reportedly achieving excellent classification capabilities. The key findings reveal a dominant negative sentiment (41.13%) towards working hours, underscoring Gen Z's concerns, further evidenced by frequently occurring terms like "resigning." However, the abstract acknowledges a "gap between training and validation performance," suggesting an area for potential improvement in model generalization, which is a crucial aspect for real-world applicability. The insights garnered from this study offer significant practical implications for a range of stakeholders, including organizations, policymakers, and human resource practitioners. By providing a data-driven understanding of Gen Z's sentiments, the research can inform the development of more flexible working-hour policies and targeted mental health support programs. While the study effectively showcases the power of transformer-based models for nuanced social media sentiment analysis, a more detailed discussion on addressing the generalization gap would further strengthen its contribution. Overall, this paper presents a timely and methodologically sound approach to understanding a critical socio-economic issue, providing valuable groundwork for future research and practical interventions aimed at enhancing the well-being of the modern workforce.

Full Text

Comments

You need to be logged in to post a comment.