Graph-Neural-Network-Based User Intent Understanding for Visual Analytics

In the design of visual analytics systems, good understanding of user intents can make systems adapt to user needs and help users better complete analytical tasks. However, user intent is difficult to observe directly. Current work tends to focus more on analyzing user behaviors and overlook the potential connections between data. In this paper, we propose an approach to understanding user intents by automatically extracting data features and combining them with user interaction history. We develop a framework for understanding user intents based on graph neural networks to support two high-level tasks: 1) real-time recommendation for the next interaction based on interaction history, and 2) real-time storytelling to characterize user intents. In our framework, we apply an SR-GATNE model based on graph neural networks to real-time recommendations and story generation. We incorporate the framework in a visual analytics system for industry analysis and evaluating the system. Results of evaluation show that our approach can help users complete the tasks better and improve their experience in analytical tasks.