This study contributes to mass customization by addressing the lack of effective methods for extracting and analyzing personalized demand indicators from user feedback. Prior studies often neglect the mapping relationship between user feedback and production characteristics, the practical integration of user experience data with product design constraints, limiting their ability to meet diverse consumer needs. To overcome these challenges, this study proposes a data-driven approach that combines k-means clustering, sentiment analysis, and deep learning to identify key comment factors impacting the user experience of customized products. This study offers substantial scientific value by proposing a systematic and scalable method for understanding consumer preferences in mass customization. It provides manufacturers with actionable insights for improving product competitiveness and customer satisfaction. The results demonstrate that product thinness and performance are the most critical factors for personalized information technology product design, significantly influencing user satisfaction. Regression analysis confirms that while these factors, along with price, heavily affect user ratings, battery life and heat dissipation are of secondary importance.