We explore how vast collections of textual data can be systematically analyzed to extract meaningful patterns and insights. Our work focuses on techniques such as ABSA (Asepct-Based Sentiment Analysis).

Our study employs machine learning models to uncover latent patterns in design-related data and make predictive analyses. We utilize algorithms such as classification, network analysis, and deep learning.

We investigate how data-driven approaches can guide the design process. By integrating text mining and machine learning, we aim to create intelligent systems that assist designers throughout the design process, from concept generation to evaluation.