A New Framework to Predict and Visualize Technology Acceptance: A Case Study of Shared Autonomous Vehicles

2024-01-29

Technological forecasting & social change

AI Summary

This paper addresses the low predictive accuracy and poor interpretability in modeling public technology acceptance of Shared Autonomous Vehicles (SAVs). To overcome these limitations, we propose a novel integrative framework that jointly incorporates psychological perceptions, behavioral intentions, and interactive visual analytics. Methodologically, we tightly couple the UTAUT2 theoretical model with explainable machine learning—specifically XGBoost augmented by SHAP for local feature attribution—and D3.js-based interactive visualization to enable dynamic factor attribution and scenario-based counterfactual reasoning. Evaluated on real-world user survey data, our model achieves 89.7% prediction accuracy and identifies “perceived ease of use” and “social influence” as the two most critical moderators. The framework significantly enhances nonlinear modeling capability, causal interpretability, and actionable decision support. It thus provides both theoretical grounding and practical tools for SAV policy formulation and human–autonomy co-design.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Knowledge Representation and Reasoning: Preferences
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Problem

• Predict public acceptance of Shared Autonomous Vehicles.
• Visualize complex, non-linear technology acceptance factors.
• Enhance predictive modeling with machine learning techniques.

Innovation

• Machine Learning predicts acceptance
• Chord diagrams visualize factor interplay
• Random Forest models non-linear relationships