Beyond Charging Anxiety: An Explainable Approach to Understanding User Preferences of EV Charging Stations Using Review Data

2025-07-03

AI Summary

This study addresses the optimization of electric vehicle (EV) users’ charging experience. Leveraging 17,000 real-world charging station reviews, we propose a two-tier user preference modeling framework. At the micro-level, we employ ChatGPT-4.0 for aspect-based sentiment analysis, identifying 12 critical factors—including “Facilities & Location” and “Reliability & Maintenance.” At the macro-level, we develop a LightGBM prediction model augmented with SHAP for interpretable attribution. Results indicate that positive sentiment toward “Facilities & Location” significantly enhances user satisfaction, whereas negative sentiment regarding “Reliability & Maintenance” is the primary driver of rating decline. The framework achieves fine-grained sentiment perception while ensuring model transparency and decision interpretability. It provides empirical evidence and methodological innovation to support data-driven, targeted optimization of EV charging infrastructure.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Electric vehicles (EVs) charging infrastructure is directly related to the overall EV user experience and thus impacts the widespread adoption of EVs. Understanding key factors that affect EV users' charging experience is essential for building a robust and user-friendly EV charging infrastructure. This study leverages about $17,000$ charging station (CS) reviews on Google Maps to explore EV user preferences for charging stations, employing ChatGPT 4.0 for aspect-based sentiment analysis. We identify twelve key aspects influencing user satisfaction, ranging from accessibility and reliability to amenities and pricing. Two distinct preference models are developed: a micro-level model focused on individual user satisfaction and a macro-level model capturing collective sentiment towards specific charging stations. Both models utilize the LightGBM algorithm for user preference prediction, achieving strong performance compared to other machine learning approaches. To further elucidate the impact of each aspect on user ratings, we employ SHAP (SHapley Additive exPlanations), a game-theoretic approach for interpreting machine learning models. Our findings highlight the significant impact of positive sentiment towards "amenities and location", coupled with negative sentiment regarding "reliability and maintenance", on overall user satisfaction. These insights offer actionable guidance to charging station operators, policymakers, and EV manufacturers, empowering them to enhance user experience and foster wider EV adoption.

Problem

• Understanding EV user preferences for charging stations
• Analyzing key aspects affecting charging satisfaction
• Predicting user satisfaction using machine learning models

Innovation

• Uses ChatGPT 4.0 for sentiment analysis
• Employs LightGBM algorithm for preference prediction
• Applies SHAP for model interpretation