Contemporary cities have undergone profound transformations, driven by rapid urbanization and a growing prioritization of economic growth, often at the expense of environmental sustainability and the preservation of distinctive urban identities. Although traditional remote sensing remains a cornerstone of urban change assessment, its reliance on top-down perspectives frequently limits its ability to capture the street-level dynamics and everyday experiences of urban residents. To address this limitation, this study proposes a hybrid analytical framework that combines text mining with visual analysis to examine both the perceptual and visual dimensions of urban built environment change over time. The methodology applied text mining and topic modeling to analyze expert discourse, alongside historical Street View Image (SVI) analysis to predict place perceptions, thereby uncovering evolving patterns of change across space and time. The findings show that the hybrid approach effectively captures nuanced patterns of longitudinal urban transformation. By integrating visual change detection with subjective trends derived from textual analysis, the framework reveals street-level and social dynamics that are difficult to identify using a single data source. These complementary insights demonstrate the value of combining qualitative and quantitative evidence to support more informed and context-sensitive planning interventions. Rather than replacing traditional remote sensing, the proposed framework serves as a complementary extension, adding an analytical layer that enables holistic investigation across scales, from macro-level spatial patterns to micro-scale street perceptions, and from visual change to non-visual sentiment. As such, it offers a cost-effective and adaptable tool for urban monitoring, supporting inclusive and data-driven urban planning strategies.