skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • Detecting Behavioral Failures in Emerging Electric Vehicle Infrastructure Using Supervised Text Classification Algorithms
Title: Detecting Behavioral Failures in Emerging Electric Vehicle Infrastructure Using Supervised Text Classification Algorithms
There is a growing interest in applying computational tools to the automatic discovery of social and economic behavior. For example, with decisions involving resource allocation related to public infrastructure, the ability to predict failures can allow for more efficient policy responses. In this paper, we use social data from a popular electric vehicle (EV) driver app to characterize the emerging EV charging station infrastructure. We introduce a typology of EV charging experiences collected from user reviews and deploy text classification algorithms, including convolutional neural networks (CNN), to automatically learn about potential failures. We use machine learning techniques as a pre-processing tool for econometric analyses on the quality of service delivery. After classifying the reviews into 9 main user topics and 34 subtopics, we find that the dominant issues in EV charging relate to station functionality and availability, which drive negative consumer experience. Contrary to the public discourse about EVs, range anxiety was not of large concern to existing EV drivers. Based on our findings, we move towards automated identification of failures in public charging infrastructure that can significantly reduce research evaluation costs through relatively simple computational solutions.  more » « less
Award ID(s):
1931980
PAR ID:
10165854
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Transportation Research Board Annual Meeting
Volume:
20-03461
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, CARMA 2020, 3rd International Conference on Advanced Research Methods and Analytics)
    Mobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications are used by drivers to locate charging stations in public spaces, pay for charging transactions, and engage with other users. This activity generates a rich source of data about charging infrastructure and behavior. However, an increasing share of this data is stored as unstructured text—inhibiting our ability to interpret behavior in real-time. In this article, we implement recent transformer-based deep learning algorithms, BERT and XLnet, that have been tailored to automatically classify short user reviews about EV charging experiences. We achieve classification results with a mean accuracy of over 91% and a mean F1 score of over 0.81 allowing for more precise detection of topic categories, even in the presence of highly imbalanced data. Using these classification algorithms as a pre-processing step, we analyze a U.S. national dataset with econometric methods to discover the dominant topics of discourse in charging infrastructure. After adjusting for station characteristics and other factors, we find that the functionality of a charging station is the dominant topic among EV drivers and is more likely to be discussed at points-of-interest with negative user experiences. 
    more » « less
  2. ; ; ; ; ; ; ; (, 2025 Transportation Research Board Annual Meeting)
    In this study, we raise the concern that current understandings of user perceptions and decision-making processes may jeopardize the sustainable development of charging infrastructure and wider EV adoption. This study addresses three main concerns: (1) most research focuses solely on battery electric vehicle users, neglecting plug-in hybrid (PHEV) and non-EV owners, thus failing to identify common preferences or transitional perceptions that could guide an inclusive development plan; (2) potential factors influencing charging station selection, such as the availability of nearby amenities and the role of information from social circles and user reviews, are often overlooked; and (3) used methods cannot reveal individual items' importance or uncover patterns between them as they often combine or transform the original items. To address these gaps, we conducted a survey experiment among 402 non-EV, PHEV and EV users and applied network analysis to capture their charging station selection decision-making processes. Our findings reveal that non-EV and PHEV users prioritize accessibility, whereas EV owners focus on the number of chargers. Furthermore, certain technical features, such as vehicle-to-grid capabilities, are commonly disregarded, while EV users place significant importance on engaging in amenities while charging. We also report an evolution of preferences, with users shifting their priorities on different types of information as they transition from non-EV and PHEV to EV ownership. Our results highlight the necessity for adaptive infrastructure strategies that consider the evolving preferences of different user groups to foster sustainable and equitable charging infrastructure development and broader adoption of EVs. 
    more » « less
  3. (, Proceedings of the Transportation Research Board (TRB) annual meeting)
    By displacing gasoline and diesel fuels, electric cars and fleets offer significant public health benefits by reducing emissions from the transportation sector. However, public confidence in the reliability of charging infrastructure remains a fundamental barrier to adoption. Using large-scale social data and machine learning based on 12,720 U.S. electric vehicle charging stations, we provide national evidence on how well the existing charging infrastructure is serving the needs of the expanding population of EV drivers in 651 core-based statistical areas in the United States. Contrary to predictions, we find that stations at private charging locations do not outperform public charging locations provided by government. We also find evidence of higher negative sentiment in the dense urban centers, where issues of charge rage and congestion may be the most prominent. Overall, 40% of drivers using mobility apps have faced negative experiences at EV charging stations, a problem that needs to be fixed as the market expands. 
    more » « less
  4. ; (, American Society of Civil Engineers)
    The site selection of public electric vehicle charging stations (EVCS) will have a long-lasting impact on people’s access to and use of EV, and thus long-term social equity. Since it is hardly possible to reinstall a public EVCS once it is built, site selections for EVCS should consider a fair share of benefits. In this respect, this research explores the evaluation criteria of social equity for guiding public EVCS installations through a comprehensive systematic review. This study will provide a comprehensive social aspect which synthesizes evaluation indicators and socioeconomic and demographic variables regarding EVCS installations toward fair infrastructure investment. The proposed complete social equity criteria can be utilized to investigate the patterns of community and social features so that socially acceptable, preferable, and equitable sites for EVCS can be suggested. This study will advance the body of knowledge on planning, design, and installation decisions of equitable public infrastructure. 
    more » « less
  5. ; ; ; ; (, Research Square)
    Abstract Unlike refueling at gas stations, charging an electric vehicle (EV) requires significantly more time, ranging from 20 minutes to over an hour, even with the fastest chargers. This prolonged charging duration introduces unique complexities to the fundamental understanding of public charging station (PCS) accessibility, raises questions about the ongoing relevance of spatial proximity for different population groups, and highlights the need to consider amenities near PCS that users can access along their daily routines. To account for these critical distinctions, we introduce visit-based accessibility, a metric that evaluates PCS availability relative to amenities frequented during urban routine activities. Leveraging data from over 28,000 PCSs, 5.2 million points of interest (POIs), and mobility patterns from more than 35 million cell phone users across 20 major U.S. metropolitan areas, we reveal a striking mismatch between PCS locations and the spatial proximity to and the daily needs of their intended users. While existing PCSs are spatially proximate to lower-income communities, our visit-based measure reveals significant disparities, as these communities' routine activities align significantly less with PCS locations. Furthermore, when considering dwell time at nearby amenities, higher-income communities exhibit better alignment of PCSs with routine activities and longer dwell times at nearby POIs, which are also the most extensively covered by existing PCSs. Finally, our analysis reveals that experienced income and racial segregation are likely the major impedance for accessing PCSs that are spatially adjacent, which highlights a hidden social barrier where greater divergence from typical social encounters near charging infrastructure is associated with lower visit rates to PCSs. These findings underscore the necessity for targeted strategies to ensure equitable access to charging infrastructure, addressing both spatial and functional disparities to promote sustainable and inclusive urban development. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email