In today’s technology-based society, people share their opinions on online social media platforms, which can be used as data for sentiment analysis. One of the most popular platforms for obtaining publicly accessible data is X. This study analyzes public views of the Ministry of Finance (MoF) by examining 9,543 tweets gathered from February to September 2025. The data collected was preprocessed through cleaning, name entities grouping, and keywords filtering, then evaluated using IndoBERTweet, and keywords were extracted using the Term Frequency-Inverse Document Frequency (TF-IDF). For topic modelling, Latent Dirichlet Allocation (LDA) was used, and sentiment distributions were tracked over time through temporal aggregation. To obtain more specific public opinion sentiment analysis, a neutral classification was added to differentiate from the previous studies that used only positive and negative classifications. To support this approach, a pre-trained model with three sentiment classifications was used. The results show that neutral sentiment dominated the tweets followed by negative sentiment then positive sentiment, especially during the transition to the new Ministry of Finance, showing the relevance of real-world events to online public opinion on X. Based on topic trends, public opinion shows the trend change from fiscal policy and leadership to criticism and leadership change.