<![CDATA[This study discusses public perceptions of the increasingly widespread use of machine-based technology in everyday life. One approach to understanding this perception is through sentiment analysis conducted on public opinion on social media. Using machine learning methods, this study classifies public sentiment into three categories: positive, negative, and neutral. Data was collected through the Twitter social media stage and processed using the CRISP-DM approach. Three algorithms were used in the classification, namely Bolster Vector Machine (SVM), Credulous Bayes, and Choice Tree. The evaluation results showed that SVM provided the highest accuracy in classifying sentiment data. The majority of public opinion was neutral, but there were concerns regarding social and ethical impacts. This study contributes to a general understanding of public perceptions of machine-based technology that are increasingly dominating various sectors.]]>
Copyrights © 2025
