<![CDATA[The development of the MSMEs sector plays a crucial role in national economic growth. It not only supports the regional economy but also significantly impacts and contributes to job creation and equitable income distribution. However, one of the primary obstacles faced by MSMEs is limited access to financing or loans. To address this issue, many government and private institutions provide financing and mentoring programs. This study focuses on the analysis of sentiment opinions regarding assisted MSMEs loans in the Bangka Belitung Islands Province using the Cross-Industry Standard Process for Data Mining approach and the Multinomial Naïve Bayes algorithm, was utilized for opinion sentiment analysis on assisted MSME loans, with a total of 1,112 reviews collected through surveys and data from assisted MSMEs, such as Witel. This study successfully implemented the CRISP-DM framework and the Multinomial Naïve Bayes algorithm to analyze public opinion sentiment toward assisted MSME loan programs in the Bangka Belitung Islands Province. Achieving an accuracy of 96.02%, this model proves to be highly effective and efficient in extracting and classifying survey-based opinion data. The primary scientific contribution of this research is the successful integration of a structured data mining approach with local economic policy analysis. However, a trade-off was identified in the Negative Recall of 0.79, indicating that 21% of negative opinions were missed due to a class imbalance where positive opinion data significantly outnumbered negative opinions in the survey. Overall, this approach yielded exceptionally high evaluation metrics, achieving a Positive Recall of 1.00 and a Negative Precision of 1.00.]]>
