Application of Sentiment Analysis and Data-Driven User Profiling in Product Iteration Design

Abstract

Our study employs sentiment analysis and data-driven methodologies to construct precise user profiles and apply them to product iteration design, aiming to enhance marketing effectiveness and user satisfaction. The research data comprises 178,563 user comments and 42,786 social media posts. Sentiment features are extracted using advanced sentiment analysis algorithms such as BERT and Transformer. These features are combined with user behavior data and classified into five primary groups using the K-means clustering algorithm, each representing distinct user needs and sentiment tendencies. Based on the user profiles, three product iteration schemes were designed and implemented. The effectiveness of these iterations was validated through A/B testing, resulting in significant improvements in user satisfaction and usage rates. Regression analysis reveals that both sentiment scores and user behavior features have a significant positive impact on user satisfaction. The findings demonstrate that combining sentiment analysis with data-driven user profiling plays a crucial role in product design and marketing, offering new insights for optimizing products and enhancing competitiveness.