Graph Neural Networks for User Satisfaction Classification in Human-Computer Interaction

2025-11-06

AI Summary

Modeling user satisfaction in human-computer interaction is challenging due to complex behavioral dependencies and multidimensional heterogeneous features. Method: This paper proposes an end-to-end Graph Neural Network (GNN)-based framework that constructs a structured interaction graph from user action sequences and interface elements, jointly modeling nodes (user actions/interface components) and edges (interaction relations). It integrates graph convolution, attention mechanisms, and global pooling to synergistically optimize local pattern recognition and global contextual awareness. Contribution/Results: Compared to conventional sequential or statistical models, the approach significantly enhances representation capability for dynamic, sparse, and non-Euclidean interaction data. Evaluated on a Kaggle public dataset, it outperforms mainstream baselines across accuracy, F1-score, AUC, and precision—demonstrating both effectiveness and generalizability of graph-structured modeling for satisfaction prediction.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Constraint Satisfaction and Optimization: Satisfiability
• Machine Learning: Graph-based Machine Learning

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

This study focuses on the problem of user satisfaction classification and proposes a framework based on graph neural networks to address the limitations of traditional methods in handling complex interaction relationships and multidimensional features. User behaviors, interface elements, and their potential connections are abstracted into a graph structure, and joint modeling of nodes and edges is used to capture semantics and dependencies in the interaction process. Graph convolution and attention mechanisms are introduced to fuse local features and global context, and global pooling with a classification layer is applied to achieve automated satisfaction classification. The method extracts deep patterns from structured data and improves adaptability and robustness in multi-source heterogeneous and dynamic environments. To verify effectiveness, a public user satisfaction survey dataset from Kaggle is used, and results are compared with multiple baseline models across several performance metrics. Experiments show that the method outperforms existing approaches in accuracy, F1-Score, AUC, and Precision, demonstrating the advantage of graph-based modeling in satisfaction prediction tasks. The study not only enriches the theoretical framework of user modeling but also highlights its practical value in optimizing human-computer interaction experience.

Problem

• Classifying user satisfaction by modeling complex interaction relationships in HCI
• Addressing limitations of traditional methods with graph neural networks
• Improving accuracy and robustness in dynamic multi-source environments

Innovation

• Graph neural networks model user interaction relationships
• Graph convolution and attention fuse local and global features
• Global pooling and classification enable automated satisfaction assessment