<![CDATA[This research is motivated by the increasing need for accurate, fast, and adaptive political data analysis models to address developments in digital technology, particularly in integrating visual and non-visual data. Theoretically, this research draws on machine learning-based analytical approaches, data integration theory, and concepts of information processing in intelligent systems. The urgency of this research lies in the limitations of conventional methods, which exhibit accuracy fluctuations in the range of 78%–82% and are unable to capture the complexity of voter preference patterns. The novelty of this research lies in the development of a predictive model based on the integration of textual questionnaire data and image data, which can significantly improve analysis accuracy. The research problem focuses on the model's effectiveness in improving accuracy, consistency, and processing time efficiency compared to conventional methods. The purpose of this research is to test model performance and identify the advantages of data integration in region-based political analysis. The method used is a quantitative approach with statistical output simulations similar to SPSS. The results showed that the model produced an average accuracy of 91.3% with a standard deviation of 0.56, an average processing time of 18 hours with a standard deviation of 0.82, and an increase in data interpretation accuracy of ±28% compared to conventional methods. In conclusion, the model proved to be more stable, efficient, and superior in producing comprehensive data-driven analysis.]]>
Copyrights © 2026
