KLASIFIKASI OPINI DARING IMPLEMENTASI TEKNOLOGI VIDEO UNDERSTANDING UNTUK KESELAMATAN KERJA INDUSTRI 4.0

Abstrak

The advancement of Industry 4.0 technologies has accelerated the adoption of artificial intelligence, including video understanding, to improve efficiency and workplace safety in industrial environments. However, the implementation of this technology has generated diverse public opinions, particularly on social media platforms such as X. This study aims to identify public perceptions regarding the use of video understanding to ensure workplace safety through online opinion classification. Data were collected from X using a web scraping technique based on selected keywords. The dataset then underwent a series of preprocessing steps, including case folding, filtering, tokenization, normalization, stopword removal, and stemming. Feature representation was carried out using TF-IDF, followed by classification with the Multinomial Naive Bayes algorithm. The model was chosen due to its suitability in handling short and unstructured text, which aligns with the characteristics of tweets. Model performance was evaluated using accuracy, precision, recall, F1-score, and a confusion matrix. The results show that the majority of public opinions are neutral, with a smaller proportion of positive and negative sentiments. The model achieved a high performance with 98% accuracy and strong precision, recall, and F1-score across all sentiment classes. These findings provide insights into public acceptance of video understanding in workplace safety and can serve as valuable input for industry stakeholders in designing transparent and adaptive implementation strategies. Furthermore, this study highlights the contribution of data science in understanding societal perceptions of digital technologies in the modern era.

Identifier

• DOI: https://doi.org/10.31949/j-ensitec.v12i01.16227
• OpenAlex: https://openalex.org/W7125370951