Deep learning-based social media mining for user experience analysis: A case study of smart home products

Abstract

Understanding and enhancing user experience (UX) is crucial for new product innovation. Abundant user-generated content (UGC) from social media contains information about customers' product experience and provides an alternative channel for firms to understand UX and improve their products. However, only a few studies have focused on this issue. This research develops a deep learning-based methodology to identify the major UX elements from UGC and analyze their relationships for improving customers' product experiences. The state-of-the-art deep learning approach BERT (Bidirectional Encoder Representations from Transformers) is used to identify the major UX elements from UGC. The Plutchik's wheel of emotions model is used to elaborate users' complex emotional experiences. Association rule mining (ARM) is employed to extract significant patterns of association between the major UX elements. The UGC data from an online discussion group for smart home products is used as an example. The results demonstrate that the methodology can effectively identify relevant UX content and the important relationships between major UX elements for improving products and services. Further, the methodology can help companies better understand UX based on multiple emotional states and develop actions that respond more effectively to user behaviors triggered by their emotional states.