Artificial Intelligence (AI) has been trained to read user reviews to identify infrastructure gaps in electric vehicle (EV) charging stations.
Although EVs are key to reducing air pollution and greenhouse gas emissions, the lack of confidence in charging services deters many people from going electric.
In a bid to tackle this, researchers have developed an AI that can accurately identify places where there are insufficient or out-of-service stations.
With the aid of their AI, the researchers were able to predict whether a specific station was functional on a particular day.
As opposed to previous charging infrastructure performance evaluation studies that rely on costly and infrequent self-reported surveys, AI can reduce research costs while providing real-time standardised data.
The AI achieved a 91% accuracy and high learning efficiency in parsing the reviews in minutes.
The new method can also give insight into consumers behaviour, enabling rapid policy analysis and making infrastructure management easier for the government and companies.
Omar Asensio, lead author of the study said: ‘We’re spending billions of both public and private dollars on electric vehicle infrastructure.
‘But we really don’t have a good understanding of how well these investments are serving the public and public interest.’
Co-author of the study, Sameer Dharur added: ‘When users are engaging and sharing information about charging experiences, they are often engaging in prosocial or pro-environmental behaviour, which gives us rich behavioural information for machine learning.
‘But compared to analysing data tables, texts can be challenging for computers to process. A review could be as short as three words. It could also be as long as 25 or 30 words with misspellings and multiple topics, sometimes even throw smiley faces or emojis into the texts.’
In related news, a survey conducted by Uswitch revealed that drivers concerned about the number of EV charge points.
Photo Credit – Pixabay