Human-Computer Interaction in Smart Devices: Leveraging Sentiment Analysis and Knowledge Graphs for Personalized User Experiences

This study proposes a user experience analysis method for smart devices based on user behavior pattern analysis and device response optimization, aiming to improve the response accuracy and user satisfaction of smart devices in human-computer interaction. Through the collection of interaction data between users and smart devices, the study delves into the application of sentiment analysis and knowledge graphs within smart devices. This research analyzes user behavior patterns, emotional shifts, and the device’s response strategies. The experimental results show that by optimizing the device response strategy, not only the response accuracy is improved but also the user satisfaction is significantly improved. In particular, when the device can make personalized feedback according to the user's emotional changes, the interaction effect is significantly improved. In addition, the experiment also verifies the device's responsiveness under different emotional states, demonstrating the optimized device's accurate understanding and intelligent response to user needs. This study provides new ideas for emotional perception, demand prediction, and personalized interaction design of smart devices, and lays a theoretical foundation for future user experience optimization based on artificial intelligence.